docling.rs-wasm 0.50.0

package/bundler/docling_wasm_bg.wasm.d.ts

@@ -0,0 +1,33 @@
+/* tslint:disable */
+/* eslint-disable */
+export const memory: WebAssembly.Memory;
+export const convert: (a: number, b: number, c: number, d: number, e: number, f: number, g: number, h: number, i: number) => [number, number, number, number];
+export const start: () => void;
+export const supported_extensions: () => [number, number];
+export const version: () => [number, number];
+export const ocr_image: (a: number, b: number, c: number, d: number, e: any, f: number, g: number) => any;
+export const __wbg_digitalconverter_free: (a: number, b: number) => void;
+export const __wbg_scannedconverter_free: (a: number, b: number) => void;
+export const convert_scanned_image: (a: number, b: number, c: number, d: number, e: number, f: number, g: any, h: any, i: number, j: number, k: number, l: number) => any;
+export const digitalconverter_addPageTf: (a: number, b: number, c: number, d: number, e: number, f: number, g: number, h: any, i: any, j: number) => any;
+export const digitalconverter_add_page: (a: number, b: number, c: number, d: number, e: number, f: number, g: number, h: any, i: number) => any;
+export const digitalconverter_finish: (a: number, b: number, c: number, d: number, e: number, f: number, g: number) => [number, number, number, number];
+export const digitalconverter_new: (a: number, b: number, c: number, d: number) => [number, number, number];
+export const digitalconverter_page_count: (a: number) => number;
+export const digitalconverter_setDict: (a: number, b: number, c: number) => void;
+export const scannedconverter_addPageTf: (a: number, b: number, c: number, d: number, e: number, f: number, g: any, h: any, i: any) => any;
+export const scannedconverter_add_page: (a: number, b: number, c: number, d: number, e: number, f: number, g: any, h: any) => any;
+export const scannedconverter_finish: (a: number, b: number, c: number, d: number, e: number, f: number, g: number) => [number, number, number, number];
+export const scannedconverter_new: (a: number, b: number) => number;
+export const scannedconverter_page_count: (a: number) => number;
+export const wasm_bindgen_c5dab95b9564c094___convert__closures_____invoke___wasm_bindgen_c5dab95b9564c094___JsValue__core_9b3796e30d99ddb7___result__Result_____wasm_bindgen_c5dab95b9564c094___JsError___true_: (a: number, b: number, c: any) => [number, number];
+export const wasm_bindgen_c5dab95b9564c094___convert__closures_____invoke___js_sys_29633ec172849407___Function_fn_wasm_bindgen_c5dab95b9564c094___JsValue_____wasm_bindgen_c5dab95b9564c094___sys__Undefined___js_sys_29633ec172849407___Function_fn_wasm_bindgen_c5dab95b9564c094___JsValue_____wasm_bindgen_c5dab95b9564c094___sys__Undefined_______true_: (a: number, b: number, c: any, d: any) => void;
+export const __wbindgen_malloc: (a: number, b: number) => number;
+export const __wbindgen_realloc: (a: number, b: number, c: number, d: number) => number;
+export const __wbindgen_exn_store: (a: number) => void;
+export const __externref_table_alloc: () => number;
+export const __wbindgen_externrefs: WebAssembly.Table;
+export const __wbindgen_free: (a: number, b: number, c: number) => void;
+export const __wbindgen_destroy_closure: (a: number, b: number) => void;
+export const __externref_table_dealloc: (a: number) => void;
+export const __wbindgen_start: () => void;

package/package.json

@@ -0,0 +1,50 @@
+{
+  "name": "docling.rs-wasm",
+  "version": "0.50.0",
+  "description": "In-browser document conversion: DOCX, HTML, XLSX, PPTX, EPUB, Markdown, … and the text layer of PDFs → Markdown / docling JSON / DocLang, fully client-side (docling.rs compiled to WebAssembly)",
+  "license": "MIT",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/docling-project/docling.rs.git",
+    "directory": "crates/docling-wasm"
+  },
+  "homepage": "https://github.com/docling-project/docling.rs/tree/master/crates/docling-wasm#readme",
+  "keywords": [
+    "docling",
+    "document",
+    "conversion",
+    "markdown",
+    "pdf",
+    "docx",
+    "xlsx",
+    "pptx",
+    "wasm",
+    "webassembly",
+    "browser",
+    "ocr"
+  ],
+  "type": "module",
+  "main": "bundler/docling_wasm.js",
+  "types": "bundler/docling_wasm.d.ts",
+  "exports": {
+    ".": {
+      "types": "./bundler/docling_wasm.d.ts",
+      "default": "./bundler/docling_wasm.js"
+    },
+    "./web": {
+      "types": "./web/docling_wasm.d.ts",
+      "default": "./web/docling_wasm.js"
+    },
+    "./web/docling_wasm_bg.wasm": "./web/docling_wasm_bg.wasm",
+    "./bundler/docling_wasm_bg.wasm": "./bundler/docling_wasm_bg.wasm"
+  },
+  "sideEffects": [
+    "./bundler/docling_wasm.js"
+  ],
+  "files": [
+    "bundler",
+    "web",
+    "README.md",
+    "LICENSE"
+  ]
+}

package/web/docling_wasm.d.ts

@@ -0,0 +1,190 @@
+/* tslint:disable */
+/* eslint-disable */
+
+/**
+ * A digital PDF being converted page by page. Construct it from the file's
+ * bytes (the text layer is parsed once, in Rust), then feed the rasterized
+ * pages in order.
+ */
+export class DigitalConverter {
+    free(): void;
+    [Symbol.dispose](): void;
+    /**
+     * [`add_page`](Self::add_page) with TableFormer for the table regions whose
+     * geometric reconstruction looks unreliable.
+     */
+    addPageTf(index: number, rgba: Uint8Array, px_w: number, px_h: number, scale: number, layout: any, tf: any, rec?: any | null): Promise<void>;
+    /**
+     * Convert page `index` (0-based) given its rendered bitmap: layout
+     * detection plus geometric tables. `scale` is the raster's pixels per PDF
+     * point (2.0 for pdf.js `{scale: 2}`). With `rec` (and a dictionary at
+     * construction), embedded raster pictures that carry no text cells are
+     * OCR'd — the text a digital page's images hide from its text layer.
+     */
+    add_page(index: number, rgba: Uint8Array, px_w: number, px_h: number, scale: number, layout: any, rec?: any | null): Promise<void>;
+    /**
+     * Assemble the converted pages into a document and render it as `"md"`
+     * (default), `"json"` or `"doclang"`, with `images` picking how pictures
+     * render in Markdown. Resets the converter.
+     */
+    finish(name: string, to?: string | null, images?: string | null): string;
+    /**
+     * Parse the PDF's text layer. Fails when there is none — the caller should
+     * fall back to the scanned pipeline, exactly as the demo page does.
+     * `dict` (optional) is the recognition dictionary text; with it and a
+     * `RecSession` on `add_page`, embedded raster pictures get OCR'd too.
+     */
+    constructor(bytes: Uint8Array, dict?: string | null);
+    /**
+     * Pages the text parser found.
+     */
+    page_count(): number;
+    /**
+     * Install the recognition dictionary after construction — the host probes
+     * the text layer first (the constructor throws on a scan) and only then
+     * fetches the recognition model + dictionary.
+     */
+    setDict(dict: string): void;
+}
+
+/**
+ * Multi-page scanned-document converter (lite profile). Feed pages in
+ * order, then [`finish`](Self::finish) — cross-page paragraph continuations
+ * merge exactly like the native pipeline.
+ */
+export class ScannedConverter {
+    free(): void;
+    [Symbol.dispose](): void;
+    /**
+     * Convert one page with TableFormer (#157 stage 3): table regions get the
+     * ONNX table-structure model + docling's cell matcher instead of the
+     * geometric reconstruction. `tf` is the JS-side session over the encoder /
+     * decoder / bbox graphs.
+     */
+    addPageTf(rgba: Uint8Array, px_w: number, px_h: number, scale: number, layout: any, rec: any, tf: any): Promise<void>;
+    /**
+     * Convert one page (lite profile — geometric tables): `rgba` is the
+     * rendered bitmap (canvas ImageData), `scale` its pixels-per-PDF-point
+     * (2.0 for pdf.js `{scale: 2}`; 1.0 for a standalone image).
+     */
+    add_page(rgba: Uint8Array, px_w: number, px_h: number, scale: number, layout: any, rec: any): Promise<void>;
+    /**
+     * Assemble the accumulated pages into the final document and render it
+     * as `"md"` (default), `"json"` or `"doclang"` — the same three the
+     * declarative [`crate::convert`] entry point offers. `images` picks how
+     * cropped figures render in Markdown (`"placeholder"` | `"embedded"`),
+     * like [`crate::convert`]. Resets the converter.
+     */
+    finish(name: string, to?: string | null, images?: string | null): string;
+    /**
+     * `dict` is the recognition dictionary text (`en_dict.txt` for the
+     * default English model).
+     */
+    constructor(dict: string);
+    /**
+     * Number of pages converted so far (progress display).
+     */
+    page_count(): number;
+}
+
+/**
+ * Convert a document (as bytes + filename, the extension drives format
+ * detection) to `to`: `"md"` (Markdown, default), `"json"` (docling-core's
+ * `DoclingDocument` wire format, schema 1.10.0) or `"doclang"` (docling's
+ * DocLang XML serialization).
+ *
+ * `images` controls how pictures render in Markdown — `"placeholder"`
+ * (default) or `"embedded"` (base64 data URIs), the same option
+ * docling-serve exposes. `max_pages` converts only a PDF's first N pages
+ * (issue #80's window, first pinned to 1); other formats ignore it.
+ */
+export function convert(bytes: Uint8Array, filename: string, to?: string | null, images?: string | null, max_pages?: number | null): string;
+
+/**
+ * One-shot scanned-image conversion through the full lite profile (layout +
+ * OCR + assembly) — the browser counterpart of the native image path
+ * (a standalone image is its own page at scale 1).
+ */
+export function convert_scanned_image(bytes: Uint8Array, name: string, dict: string, layout: any, rec: any, to?: string | null, images?: string | null): Promise<string>;
+
+/**
+ * OCR a scanned image entirely in the browser: `bytes` is the image file
+ * (PNG/JPEG/…), `dict` the recognition dictionary text (`en_dict.txt` for
+ * the default English model), `session` the JS inference wrapper. Returns
+ * Markdown (default) or docling JSON per `to`, one paragraph per recognized
+ * line.
+ */
+export function ocr_image(bytes: Uint8Array, dict: string, session: any, to?: string | null): Promise<string>;
+
+export function start(): void;
+
+/**
+ * The file extensions this build can convert, as a JSON string array —
+ * handy for an `<input accept=…>` filter. PDF converts via its embedded
+ * text layer (`pdf-text`); the remaining ML formats (images, audio, METS)
+ * are excluded: they are not compiled into the wasm build.
+ */
+export function supported_extensions(): string;
+
+/**
+ * The docling.rs version this module was built from.
+ */
+export function version(): string;
+
+export type InitInput = RequestInfo | URL | Response | BufferSource | WebAssembly.Module;
+
+export interface InitOutput {
+    readonly memory: WebAssembly.Memory;
+    readonly convert: (a: number, b: number, c: number, d: number, e: number, f: number, g: number, h: number, i: number) => [number, number, number, number];
+    readonly start: () => void;
+    readonly supported_extensions: () => [number, number];
+    readonly version: () => [number, number];
+    readonly ocr_image: (a: number, b: number, c: number, d: number, e: any, f: number, g: number) => any;
+    readonly __wbg_digitalconverter_free: (a: number, b: number) => void;
+    readonly __wbg_scannedconverter_free: (a: number, b: number) => void;
+    readonly convert_scanned_image: (a: number, b: number, c: number, d: number, e: number, f: number, g: any, h: any, i: number, j: number, k: number, l: number) => any;
+    readonly digitalconverter_addPageTf: (a: number, b: number, c: number, d: number, e: number, f: number, g: number, h: any, i: any, j: number) => any;
+    readonly digitalconverter_add_page: (a: number, b: number, c: number, d: number, e: number, f: number, g: number, h: any, i: number) => any;
+    readonly digitalconverter_finish: (a: number, b: number, c: number, d: number, e: number, f: number, g: number) => [number, number, number, number];
+    readonly digitalconverter_new: (a: number, b: number, c: number, d: number) => [number, number, number];
+    readonly digitalconverter_page_count: (a: number) => number;
+    readonly digitalconverter_setDict: (a: number, b: number, c: number) => void;
+    readonly scannedconverter_addPageTf: (a: number, b: number, c: number, d: number, e: number, f: number, g: any, h: any, i: any) => any;
+    readonly scannedconverter_add_page: (a: number, b: number, c: number, d: number, e: number, f: number, g: any, h: any) => any;
+    readonly scannedconverter_finish: (a: number, b: number, c: number, d: number, e: number, f: number, g: number) => [number, number, number, number];
+    readonly scannedconverter_new: (a: number, b: number) => number;
+    readonly scannedconverter_page_count: (a: number) => number;
+    readonly wasm_bindgen_c5dab95b9564c094___convert__closures_____invoke___wasm_bindgen_c5dab95b9564c094___JsValue__core_9b3796e30d99ddb7___result__Result_____wasm_bindgen_c5dab95b9564c094___JsError___true_: (a: number, b: number, c: any) => [number, number];
+    readonly wasm_bindgen_c5dab95b9564c094___convert__closures_____invoke___js_sys_29633ec172849407___Function_fn_wasm_bindgen_c5dab95b9564c094___JsValue_____wasm_bindgen_c5dab95b9564c094___sys__Undefined___js_sys_29633ec172849407___Function_fn_wasm_bindgen_c5dab95b9564c094___JsValue_____wasm_bindgen_c5dab95b9564c094___sys__Undefined_______true_: (a: number, b: number, c: any, d: any) => void;
+    readonly __wbindgen_malloc: (a: number, b: number) => number;
+    readonly __wbindgen_realloc: (a: number, b: number, c: number, d: number) => number;
+    readonly __wbindgen_exn_store: (a: number) => void;
+    readonly __externref_table_alloc: () => number;
+    readonly __wbindgen_externrefs: WebAssembly.Table;
+    readonly __wbindgen_free: (a: number, b: number, c: number) => void;
+    readonly __wbindgen_destroy_closure: (a: number, b: number) => void;
+    readonly __externref_table_dealloc: (a: number) => void;
+    readonly __wbindgen_start: () => void;
+}
+
+export type SyncInitInput = BufferSource | WebAssembly.Module;
+
+/**
+ * Instantiates the given `module`, which can either be bytes or
+ * a precompiled `WebAssembly.Module`.
+ *
+ * @param {{ module: SyncInitInput }} module - Passing `SyncInitInput` directly is deprecated.
+ *
+ * @returns {InitOutput}
+ */
+export function initSync(module: { module: SyncInitInput } | SyncInitInput): InitOutput;
+
+/**
+ * If `module_or_path` is {RequestInfo} or {URL}, makes a request and
+ * for everything else, calls `WebAssembly.instantiate` directly.
+ *
+ * @param {{ module_or_path: InitInput | Promise<InitInput> }} module_or_path - Passing `InitInput` directly is deprecated.
+ *
+ * @returns {Promise<InitOutput>}
+ */
+export default function __wbg_init (module_or_path?: { module_or_path: InitInput | Promise<InitInput> } | InitInput | Promise<InitInput>): Promise<InitOutput>;