pdf-oxide-wasm 0.3.10

package/README.md

@@ -0,0 +1,47 @@
+# pdf-oxide-wasm
+
+High-performance PDF text extraction and manipulation via WebAssembly. Built on the [PDF Oxide](https://github.com/yfedoseev/pdf_oxide) Rust core.
+
+## Quick Start
+
+```javascript
+const { WasmPdfDocument } = require("pdf-oxide-wasm");
+const fs = require("fs");
+
+const bytes = new Uint8Array(fs.readFileSync("document.pdf"));
+const doc = new WasmPdfDocument(bytes);
+
+console.log(`Pages: ${doc.pageCount()}`);
+console.log(doc.extractText(0));
+
+doc.free();
+```
+
+### ESM
+
+```javascript
+import { WasmPdfDocument } from "pdf-oxide-wasm";
+
+const bytes = new Uint8Array(await fs.promises.readFile("document.pdf"));
+const doc = new WasmPdfDocument(bytes);
+const text = doc.extractText(0);
+doc.free();
+```
+
+## Features
+
+- Text extraction (plain text, Markdown, HTML)
+- Character-level and span-level extraction with positions
+- PDF creation from Markdown, HTML, text, and images
+- Form field extraction and filling
+- PDF editing (metadata, rotation, cropping, annotations)
+- Encryption (AES-256)
+- Search with regex support
+
+## Documentation
+
+Full API reference and examples: [Getting Started (WASM)](https://github.com/yfedoseev/pdf_oxide/blob/main/docs/getting-started-wasm.md)
+
+## License
+
+MIT OR Apache-2.0

package/package.json

@@ -0,0 +1,27 @@
+{
+  "name": "pdf-oxide-wasm",
+  "version": "0.3.10",
+  "description": "High-performance PDF text extraction and manipulation via WebAssembly",
+  "license": "MIT OR Apache-2.0",
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/yfedoseev/pdf_oxide"
+  },
+  "homepage": "https://github.com/yfedoseev/pdf_oxide/blob/main/docs/getting-started-wasm.md",
+  "files": [
+    "pdf_oxide_bg.wasm",
+    "pdf_oxide.js",
+    "pdf_oxide.d.ts",
+    "pdf_oxide_bg.wasm.d.ts",
+    "README.md"
+  ],
+  "main": "pdf_oxide.js",
+  "types": "pdf_oxide.d.ts",
+  "keywords": [
+    "pdf",
+    "wasm",
+    "webassembly",
+    "text-extraction",
+    "pdf-parser"
+  ]
+}

package/pdf_oxide.d.ts

@@ -0,0 +1,404 @@
+/* tslint:disable */
+/* eslint-disable */
+
+/**
+ * Create new PDF documents from Markdown, HTML, or plain text.
+ *
+ * ```javascript
+ * const pdf = WasmPdf.fromMarkdown("# Hello\n\nWorld");
+ * const bytes = pdf.toBytes(); // Uint8Array
+ * console.log(`PDF size: ${pdf.size} bytes`);
+ * ```
+ */
+export class WasmPdf {
+    private constructor();
+    free(): void;
+    [Symbol.dispose](): void;
+    /**
+     * Create a PDF from HTML content.
+     *
+     * @param content - HTML string
+     * @param title - Optional document title
+     * @param author - Optional document author
+     */
+    static fromHtml(content: string, title?: string | null, author?: string | null): WasmPdf;
+    /**
+     * Create a PDF from image bytes (PNG, JPEG, etc.).
+     *
+     * @param data - Image file contents as a Uint8Array
+     */
+    static fromImageBytes(data: Uint8Array): WasmPdf;
+    /**
+     * Create a PDF from Markdown content.
+     *
+     * @param content - Markdown string
+     * @param title - Optional document title
+     * @param author - Optional document author
+     */
+    static fromMarkdown(content: string, title?: string | null, author?: string | null): WasmPdf;
+    /**
+     * Create a PDF from multiple image byte arrays.
+     *
+     * Each image becomes a separate page. Pass an array of Uint8Arrays.
+     *
+     * @param images_array - Array of Uint8Arrays, each containing image file bytes (PNG/JPEG)
+     */
+    static fromMultipleImageBytes(images_array: any): WasmPdf;
+    /**
+     * Create a PDF from plain text.
+     *
+     * @param content - Plain text string
+     * @param title - Optional document title
+     * @param author - Optional document author
+     */
+    static fromText(content: string, title?: string | null, author?: string | null): WasmPdf;
+    /**
+     * Get the PDF as a Uint8Array.
+     */
+    toBytes(): Uint8Array;
+    /**
+     * Get the size of the PDF in bytes.
+     */
+    readonly size: number;
+}
+
+/**
+ * A PDF document loaded from bytes for use in WebAssembly.
+ *
+ * Create an instance by passing PDF file bytes to the constructor.
+ * Call `.free()` when done to release memory.
+ */
+export class WasmPdfDocument {
+    free(): void;
+    [Symbol.dispose](): void;
+    /**
+     * Apply all redactions in the document.
+     */
+    applyAllRedactions(): void;
+    /**
+     * Apply redactions on a page (removes redacted content permanently).
+     */
+    applyPageRedactions(page_index: number): void;
+    /**
+     * Authenticate with a password to decrypt an encrypted PDF.
+     *
+     * @param password - The password string
+     * @returns true if authentication succeeded
+     */
+    authenticate(password: string): boolean;
+    /**
+     * Clear all pending erase operations for a page.
+     */
+    clearEraseRegions(page_index: number): void;
+    /**
+     * Crop margins from all pages.
+     */
+    cropMargins(left: number, right: number, top: number, bottom: number): void;
+    /**
+     * Embed a file into the PDF document.
+     *
+     * @param name - Display name for the embedded file
+     * @param data - File contents as a Uint8Array
+     */
+    embedFile(name: string, data: Uint8Array): void;
+    /**
+     * Erase (whiteout) a rectangular region on a page.
+     */
+    eraseRegion(page_index: number, llx: number, lly: number, urx: number, ury: number): void;
+    /**
+     * Erase multiple rectangular regions on a page.
+     *
+     * @param page_index - Zero-based page number
+     * @param rects - Flat array of coordinates [llx1,lly1,urx1,ury1, llx2,lly2,urx2,ury2, ...]
+     */
+    eraseRegions(page_index: number, rects: Float32Array): void;
+    /**
+     * Export form field data as FDF or XFDF bytes.
+     *
+     * @param format - "fdf" or "xfdf" (default: "fdf")
+     * @returns Uint8Array containing the exported form data
+     */
+    exportFormData(format?: string | null): Uint8Array;
+    /**
+     * Extract plain text from all pages, separated by form feed characters.
+     */
+    extractAllText(): string;
+    /**
+     * Extract character-level data from a page.
+     *
+     * Returns an array of objects with: char, bbox {x, y, width, height},
+     * font_name, font_size, font_weight, is_italic, color {r, g, b}, etc.
+     */
+    extractChars(page_index: number): any;
+    /**
+     * Extract image bytes from a page as PNG data.
+     *
+     * Returns an array of objects with: width, height, data (Uint8Array of PNG bytes), format ("png").
+     */
+    extractImageBytes(page_index: number): any;
+    /**
+     * Extract image metadata from a page.
+     *
+     * Returns an array of objects with: width, height, color_space,
+     * bits_per_component, bbox (if available). Does NOT return raw image bytes.
+     */
+    extractImages(page_index: number): any;
+    /**
+     * Extract vector paths (lines, curves, shapes) from a page.
+     *
+     * @param page_index - Zero-based page number
+     * @returns Array of path objects with bbox, stroke_color, fill_color, etc.
+     */
+    extractPaths(page_index: number): any;
+    /**
+     * Extract span-level data from a page.
+     *
+     * Returns an array of objects with: text, bbox, font_name, font_size,
+     * font_weight, is_italic, color, etc.
+     */
+    extractSpans(page_index: number): any;
+    /**
+     * Extract plain text from a single page.
+     *
+     * @param page_index - Zero-based page number
+     */
+    extractText(page_index: number): string;
+    /**
+     * Flatten all annotations in the document into page content.
+     */
+    flattenAllAnnotations(): void;
+    /**
+     * Flatten all form fields into page content.
+     *
+     * After flattening, form field values become static text and are no longer editable.
+     */
+    flattenForms(): void;
+    /**
+     * Flatten form fields on a specific page.
+     *
+     * @param page_index - Zero-based page number
+     */
+    flattenFormsOnPage(page_index: number): void;
+    /**
+     * Flatten annotations on a page into the page content.
+     */
+    flattenPageAnnotations(page_index: number): void;
+    /**
+     * Get annotations from a page.
+     *
+     * @param page_index - Zero-based page number
+     * @returns Array of annotation objects with fields like subtype, rect, contents, etc.
+     */
+    getAnnotations(page_index: number): any;
+    /**
+     * Get the value of a specific form field by name.
+     *
+     * @param name - Full qualified field name (e.g., "name" or "topmostSubform[0].Page1[0].f1_01[0]")
+     * @returns The field value: string for text, boolean for checkbox, null if not found
+     */
+    getFormFieldValue(name: string): any;
+    /**
+     * Get all form fields from the document.
+     *
+     * Returns an array of form field objects, each with:
+     * - name: Full qualified field name
+     * - field_type: "text", "button", "choice", "signature", or "unknown"
+     * - value: string, boolean, array of strings, or null
+     * - tooltip: string or null
+     * - bounds: [x1, y1, x2, y2] or null
+     * - flags: number or null
+     * - max_length: number or null
+     * - is_readonly: boolean
+     * - is_required: boolean
+     */
+    getFormFields(): any;
+    /**
+     * Get the document outline (bookmarks / table of contents).
+     *
+     * @returns Array of outline items or null if no outline exists.
+     * Each item has: { title, page (number|null), dest_name (string, optional), children (array) }
+     */
+    getOutline(): any;
+    /**
+     * Check if the document has a structure tree (Tagged PDF).
+     */
+    hasStructureTree(): boolean;
+    /**
+     * Check if the document contains XFA form data.
+     *
+     * @returns true if the document has XFA form data
+     */
+    hasXfa(): boolean;
+    /**
+     * Merge another PDF (provided as bytes) into this document.
+     *
+     * @param data - The PDF file contents to merge as a Uint8Array
+     * @returns Number of pages merged
+     */
+    mergeFrom(data: Uint8Array): number;
+    /**
+     * Load a PDF document from raw bytes.
+     *
+     * @param data - The PDF file contents as a Uint8Array
+     * @throws Error if the PDF is invalid or cannot be parsed
+     */
+    constructor(data: Uint8Array);
+    /**
+     * Get the number of pages in the document.
+     */
+    pageCount(): number;
+    /**
+     * Get the CropBox of a page as [llx, lly, urx, ury], or null if not set.
+     */
+    pageCropBox(page_index: number): any;
+    /**
+     * Get information about images on a page.
+     *
+     * Returns an array of {name, bounds: [x, y, width, height], matrix: [a, b, c, d, e, f]}.
+     */
+    pageImages(page_index: number): any;
+    /**
+     * Get page label ranges from the document.
+     *
+     * @returns Array of {start_page, style, prefix, start_value} objects, or empty array
+     */
+    pageLabels(): any;
+    /**
+     * Get the MediaBox of a page as [llx, lly, urx, ury].
+     */
+    pageMediaBox(page_index: number): Float32Array;
+    /**
+     * Get the rotation of a page in degrees (0, 90, 180, 270).
+     */
+    pageRotation(page_index: number): number;
+    /**
+     * Reposition an image on a page.
+     */
+    repositionImage(page_index: number, name: string, x: number, y: number): void;
+    /**
+     * Resize an image on a page.
+     */
+    resizeImage(page_index: number, name: string, width: number, height: number): void;
+    /**
+     * Rotate all pages by the given degrees.
+     */
+    rotateAllPages(degrees: number): void;
+    /**
+     * Rotate a page by the given degrees (adds to current rotation).
+     */
+    rotatePage(page_index: number, degrees: number): void;
+    /**
+     * Save with encryption and return the resulting PDF as bytes.
+     *
+     * @param user_password - Password required to open the document
+     * @param owner_password - Password for full access (defaults to user_password)
+     * @param allow_print - Allow printing (default: true)
+     * @param allow_copy - Allow copying text (default: true)
+     * @param allow_modify - Allow modifying (default: true)
+     * @param allow_annotate - Allow annotations (default: true)
+     */
+    saveEncryptedToBytes(user_password: string, owner_password?: string | null, allow_print?: boolean | null, allow_copy?: boolean | null, allow_modify?: boolean | null, allow_annotate?: boolean | null): Uint8Array;
+    /**
+     * Save all edits and return the resulting PDF as bytes.
+     *
+     * @returns Uint8Array containing the modified PDF
+     */
+    saveToBytes(): Uint8Array;
+    /**
+     * Search for text across all pages.
+     *
+     * @param pattern - Regex pattern or literal text to search for
+     * @param case_insensitive - Case insensitive search (default: false)
+     * @param literal - Treat pattern as literal text, not regex (default: false)
+     * @param whole_word - Match whole words only (default: false)
+     * @param max_results - Maximum results to return, 0 = unlimited (default: 0)
+     *
+     * Returns an array of {page, text, bbox, start_index, end_index, span_boxes}.
+     */
+    search(pattern: string, case_insensitive?: boolean | null, literal?: boolean | null, whole_word?: boolean | null, max_results?: number | null): any;
+    /**
+     * Search for text on a specific page.
+     */
+    searchPage(page_index: number, pattern: string, case_insensitive?: boolean | null, literal?: boolean | null, whole_word?: boolean | null, max_results?: number | null): any;
+    /**
+     * Set the document author.
+     */
+    setAuthor(author: string): void;
+    /**
+     * Set the value of a form field.
+     *
+     * @param name - Full qualified field name
+     * @param value - New value: string for text fields, boolean for checkboxes
+     */
+    setFormFieldValue(name: string, value: any): void;
+    /**
+     * Set the complete bounds of an image on a page.
+     */
+    setImageBounds(page_index: number, name: string, x: number, y: number, width: number, height: number): void;
+    /**
+     * Set the document keywords.
+     */
+    setKeywords(keywords: string): void;
+    /**
+     * Set the CropBox of a page.
+     */
+    setPageCropBox(page_index: number, llx: number, lly: number, urx: number, ury: number): void;
+    /**
+     * Set the MediaBox of a page.
+     */
+    setPageMediaBox(page_index: number, llx: number, lly: number, urx: number, ury: number): void;
+    /**
+     * Set the rotation of a page (0, 90, 180, or 270 degrees).
+     */
+    setPageRotation(page_index: number, degrees: number): void;
+    /**
+     * Set the document subject.
+     */
+    setSubject(subject: string): void;
+    /**
+     * Set the document title.
+     */
+    setTitle(title: string): void;
+    /**
+     * Convert a single page to HTML.
+     *
+     * @param page_index - Zero-based page number
+     * @param preserve_layout - Use CSS positioning to preserve layout (default: false)
+     * @param detect_headings - Whether to detect headings (default: true)
+     */
+    toHtml(page_index: number, preserve_layout?: boolean | null, detect_headings?: boolean | null, include_form_fields?: boolean | null): string;
+    /**
+     * Convert all pages to HTML.
+     */
+    toHtmlAll(preserve_layout?: boolean | null, detect_headings?: boolean | null, include_form_fields?: boolean | null): string;
+    /**
+     * Convert a single page to Markdown.
+     *
+     * @param page_index - Zero-based page number
+     * @param detect_headings - Whether to detect headings (default: true)
+     * @param include_images - Whether to include images (default: true)
+     */
+    toMarkdown(page_index: number, detect_headings?: boolean | null, include_images?: boolean | null, include_form_fields?: boolean | null): string;
+    /**
+     * Convert all pages to Markdown.
+     */
+    toMarkdownAll(detect_headings?: boolean | null, include_images?: boolean | null, include_form_fields?: boolean | null): string;
+    /**
+     * Convert a single page to plain text (with layout preservation options).
+     */
+    toPlainText(page_index: number): string;
+    /**
+     * Convert all pages to plain text.
+     */
+    toPlainTextAll(): string;
+    /**
+     * Get the PDF version as [major, minor].
+     */
+    version(): Uint8Array;
+    /**
+     * Get XMP metadata from the document.
+     *
+     * @returns Object with XMP fields (dc_title, dc_creator, etc.) or null if no XMP
+     */
+    xmpMetadata(): any;
+}