pdf-oxide-wasm 0.3.18 → 0.3.20

package/pdf_oxide.d.ts

@@ -1,690 +1,811 @@
 /* tslint:disable */
 /* eslint-disable */
 
+/**
+ * Style configuration for header/footer text.
+ */
 export class ArtifactStyle {
-  private constructor();
-  free(): void;
-  [Symbol.dispose](): void;
+    free(): void;
+    [Symbol.dispose](): void;
+    /**
+     * Set bold font for the artifact.
+     */
+    bold(): ArtifactStyle;
+    /**
+     * Set color for the artifact.
+     */
+    color(r: number, g: number, b: number): ArtifactStyle;
+    /**
+     * Set font for the artifact.
+     */
+    font(name: string, size: number): ArtifactStyle;
+    /**
+     * Create a new artifact style.
+     */
+    constructor();
 }
 
+/**
+ * Chroma subsampling format
+ */
+export enum ChromaSampling {
+    /**
+     * Both vertically and horizontally subsampled.
+     */
+    Cs420 = 0,
+    /**
+     * Horizontally subsampled.
+     */
+    Cs422 = 1,
+    /**
+     * Not subsampled.
+     */
+    Cs444 = 2,
+    /**
+     * Monochrome.
+     */
+    Cs400 = 3,
+}
+
+/**
+ * A header or footer artifact definition.
+ */
 export class WasmArtifact {
-  free(): void;
-  [Symbol.dispose](): void;
-  /**
-   * Set style for the artifact.
-   */
-  withStyle(style: ArtifactStyle): WasmArtifact;
-  /**
-   * Set vertical offset for the artifact.
-   */
-  withOffset(offset: number): WasmArtifact;
-  /**
-   * Create a new artifact.
-   */
-  constructor();
-  /**
-   * Create a left-aligned artifact.
-   */
-  static left(text: string): WasmArtifact;
-  /**
-   * Create a right-aligned artifact.
-   */
-  static right(text: string): WasmArtifact;
-  /**
-   * Create a center-aligned artifact.
-   */
-  static center(text: string): WasmArtifact;
+    free(): void;
+    [Symbol.dispose](): void;
+    /**
+     * Create a center-aligned artifact.
+     */
+    static center(text: string): WasmArtifact;
+    /**
+     * Create a left-aligned artifact.
+     */
+    static left(text: string): WasmArtifact;
+    /**
+     * Create a new artifact.
+     */
+    constructor();
+    /**
+     * Create a right-aligned artifact.
+     */
+    static right(text: string): WasmArtifact;
+    /**
+     * Set vertical offset for the artifact.
+     */
+    withOffset(offset: number): WasmArtifact;
+    /**
+     * Set style for the artifact.
+     */
+    withStyle(style: ArtifactStyle): WasmArtifact;
 }
 
+/**
+ * A footer definition.
+ */
 export class WasmFooter {
-  free(): void;
-  [Symbol.dispose](): void;
-  /**
-   * Create a new empty footer.
-   */
-  constructor();
-  /**
-   * Create a left-aligned footer.
-   */
-  static left(text: string): WasmFooter;
-  /**
-   * Create a right-aligned footer.
-   */
-  static right(text: string): WasmFooter;
-  /**
-   * Create a center-aligned footer.
-   */
-  static center(text: string): WasmFooter;
+    free(): void;
+    [Symbol.dispose](): void;
+    /**
+     * Create a center-aligned footer.
+     */
+    static center(text: string): WasmFooter;
+    /**
+     * Create a left-aligned footer.
+     */
+    static left(text: string): WasmFooter;
+    /**
+     * Create a new empty footer.
+     */
+    constructor();
+    /**
+     * Create a right-aligned footer.
+     */
+    static right(text: string): WasmFooter;
 }
 
+/**
+ * A header definition.
+ */
 export class WasmHeader {
-  free(): void;
-  [Symbol.dispose](): void;
-  /**
-   * Create a new empty header.
-   */
-  constructor();
-  /**
-   * Create a left-aligned header.
-   */
-  static left(text: string): WasmHeader;
-  /**
-   * Create a right-aligned header.
-   */
-  static right(text: string): WasmHeader;
-  /**
-   * Create a center-aligned header.
-   */
-  static center(text: string): WasmHeader;
+    free(): void;
+    [Symbol.dispose](): void;
+    /**
+     * Create a center-aligned header.
+     */
+    static center(text: string): WasmHeader;
+    /**
+     * Create a left-aligned header.
+     */
+    static left(text: string): WasmHeader;
+    /**
+     * Create a new empty header.
+     */
+    constructor();
+    /**
+     * Create a right-aligned header.
+     */
+    static right(text: string): WasmHeader;
 }
 
+/**
+ * OCR configuration for WebAssembly.
+ */
 export class WasmOcrConfig {
-  free(): void;
-  [Symbol.dispose](): void;
-  /**
-   * Create a new OCR configuration.
-   */
-  constructor();
+    free(): void;
+    [Symbol.dispose](): void;
+    /**
+     * Create a new OCR configuration.
+     */
+    constructor();
 }
 
+/**
+ * OCR engine for WebAssembly.
+ */
 export class WasmOcrEngine {
-  free(): void;
-  [Symbol.dispose](): void;
-  /**
-   * Create a new OCR engine.
-   */
-  constructor(_det_model_path: string, _rec_model_path: string, _dict_path: string, _config?: WasmOcrConfig | null);
+    free(): void;
+    [Symbol.dispose](): void;
+    /**
+     * Create a new OCR engine.
+     */
+    constructor(_det_model_path: string, _rec_model_path: string, _dict_path: string, _config?: WasmOcrConfig | null);
 }
 
+/**
+ * A complete page template with header and footer.
+ */
 export class WasmPageTemplate {
-  free(): void;
-  [Symbol.dispose](): void;
-  /**
-   * Skip rendering template on the first page.
-   */
-  skipFirstPage(): WasmPageTemplate;
-  /**
-   * Create a new page template.
-   */
-  constructor();
-  /**
-   * Set footer artifact.
-   */
-  footer(footer: WasmArtifact): WasmPageTemplate;
-  /**
-   * Set header artifact.
-   */
-  header(header: WasmArtifact): WasmPageTemplate;
+    free(): void;
+    [Symbol.dispose](): void;
+    /**
+     * Set footer artifact.
+     */
+    footer(footer: WasmArtifact): WasmPageTemplate;
+    /**
+     * Set header artifact.
+     */
+    header(header: WasmArtifact): WasmPageTemplate;
+    /**
+     * Create a new page template.
+     */
+    constructor();
+    /**
+     * Skip rendering template on the first page.
+     */
+    skipFirstPage(): WasmPageTemplate;
 }
 
+/**
+ * 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 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 image bytes (PNG, JPEG, etc.).
-   *
-   * @param data - Image file contents as a Uint8Array
-   */
-  static fromImageBytes(data: Uint8Array): 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;
-  /**
-   * Merge multiple PDF byte arrays into a single PDF.
-   *
-   * @param pdfs - Array of Uint8Array, each containing a PDF
-   * @returns WasmPdf containing all pages
-   */
-  static merge(pdfs: Uint8Array[]): WasmPdf;
-  /**
-   * Get the PDF as a Uint8Array.
-   */
-  toBytes(): Uint8Array;
-  /**
-   * 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 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 size of the PDF in bytes.
-   */
-  readonly size: number;
+    private constructor();
+    free(): void;
+    [Symbol.dispose](): void;
+    /**
+     * Open an existing PDF from bytes for editing.
+     *
+     * @param data - PDF file contents as Uint8Array
+     * @returns WasmPdf for editing
+     */
+    static fromBytes(data: Uint8Array): WasmPdf;
+    /**
+     * 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;
+    /**
+     * Merge multiple PDF byte arrays into a single PDF.
+     *
+     * @param pdfs - Array of Uint8Array, each containing a PDF
+     * @returns WasmPdf containing all pages
+     */
+    static merge(pdfs: Uint8Array[]): 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;
-  /**
-   * 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;
-  /**
-   * 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;
-  /**
-   * Get the number of pages in the document.
-   */
-  pageCount(): number;
-  /**
-   * Set the document author.
-   */
-  setAuthor(author: string): void;
-  /**
-   * Delete a page by index (0-based).
-   */
-  deletePage(index: number): void;
-  /**
-   * Deprecated: Use eraseFooter instead.
-   */
-  editFooter(page_index: number): void;
-  /**
-   * Deprecated: Use eraseHeader instead.
-   */
-  editHeader(page_index: number): void;
-  /**
-   * 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;
-  /**
-   * 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;
-  /**
-   * Rotate a page by the given degrees (adds to current rotation).
-   */
-  rotatePage(page_index: number, degrees: number): void;
-  /**
-   * 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 subject.
-   */
-  setSubject(subject: string): void;
-  /**
-   * 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;
-  /**
-   * Authenticate with a password to decrypt an encrypted PDF.
-   *
-   * @param password - The password string
-   * @returns true if authentication succeeded
-   */
-  authenticate(password: string): boolean;
-  /**
-   * Crop margins from all pages.
-   */
-  cropMargins(left: number, right: number, top: number, bottom: number): void;
-  /**
-   * Erase existing footer content.
-   *
-   * Identifies existing text in the footer area (bottom 15%) and marks it for erasure.
-   *
-   * @param page_index - Zero-based page number
-   */
-  eraseFooter(page_index: number): void;
-  /**
-   * Erase existing header content.
-   *
-   * Identifies existing text in the header area (top 15%) and marks it for erasure.
-   *
-   * @param page_index - Zero-based page number
-   */
-  eraseHeader(page_index: number): void;
-  /**
-   * Erase (whiteout) a rectangular region on a page.
-   */
-  eraseRegion(page_index: number, llx: number, lly: number, urx: number, ury: number): void;
-  /**
-   * Extract plain text from a single page.
-   *
-   * @param page_index - Zero-based page number
-   * @param region - Optional [x, y, width, height] to filter by
-   */
-  extractText(page_index: number, region: any): string;
-  /**
-   * Resize an image on a page.
-   */
-  resizeImage(page_index: number, name: string, width: number, height: number): void;
-  /**
-   * Set the document keywords.
-   */
-  setKeywords(keywords: string): void;
-  /**
-   * Get XMP metadata from the document.
-   *
-   * @returns Object with XMP fields (dc_title, dc_creator, etc.) or null if no XMP
-   */
-  xmpMetadata(): any;
-  /**
-   * 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;
-  /**
-   * 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.
-   *
-   * @param page_index - Zero-based page number
-   * @param region - Optional [x, y, width, height] to filter by
-   */
-  extractChars(page_index: number, region?: Float32Array | null): any;
-  /**
-   * Extract only straight lines from a page (v0.3.14).
-   *
-   * Identifies paths that form a single straight line segment.
-   *
-   * @param page_index - Zero-based page number
-   * @param region - Optional [x, y, width, height] to filter by
-   * @returns Array of path objects
-   */
-  extractLines(page_index: number, region?: Float32Array | null): any;
-  /**
-   * Extract specific pages to a new PDF (returns bytes).
-   */
-  extractPages(pages: Uint32Array): Uint8Array;
-  /**
-   * Extract vector paths (lines, curves, shapes) from a page.
-   *
-   * @param page_index - Zero-based page number
-   * @param region - Optional [x, y, width, height] to filter by
-   * @returns Array of path objects with bbox, stroke_color, fill_color, etc.
-   */
-  extractPaths(page_index: number, region?: Float32Array | null): any;
-  /**
-   * Extract only rectangles from a page (v0.3.14).
-   *
-   * Identifies paths that form axis-aligned rectangles.
-   *
-   * @param page_index - Zero-based page number
-   * @param region - Optional [x, y, width, height] to filter by
-   * @returns Array of path objects
-   */
-  extractRects(page_index: number, region?: Float32Array | null): 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, region?: Float32Array | null): any;
-  /**
-   * Extract word-level data from a page.
-   *
-   * Returns an array of objects with: text, bbox, font_name, font_size,
-   * font_weight, is_italic, is_bold.
-   */
-  extractWords(page_index: number, region?: Float32Array | null): any;
-  /**
-   * Flatten all form fields into page content.
-   *
-   * After flattening, form field values become static text and are no longer editable.
-   */
-  flattenForms(): void;
-  /**
-   * Get the CropBox of a page as [llx, lly, urx, ury], or null if not set.
-   */
-  pageCropBox(page_index: number): any;
-  /**
-   * Get the rotation of a page in degrees (0, 90, 180, 270).
-   */
-  pageRotation(page_index: number): number;
-  /**
-   * Save the modified PDF and return as bytes.
-   * `saveToBytes()` is the original method; `save()` is a convenience alias.
-   *
-   * @returns Uint8Array containing the modified PDF
-   */
-  saveToBytes(): Uint8Array;
-  /**
-   * Convert a single page to plain text (with layout preservation options).
-   */
-  toPlainText(page_index: number): string;
-  /**
-   * 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.
-   *
-   * @param page_index - Zero-based page number
-   * @param region - Optional [x, y, width, height] to filter by
-   */
-  extractImages(page_index: number, region?: Float32Array | null): any;
-  /**
-   * Extract tables from a page (v0.3.14).
-   *
-   * @param page_index - Zero-based page number
-   * @param region - Optional [x, y, width, height] to filter by
-   */
-  extractTables(page_index: number, region?: Float32Array | null): any;
-  /**
-   * Get the MediaBox of a page as [llx, lly, urx, ury].
-   */
-  pageMediaBox(page_index: number): Float32Array;
-  /**
-   * Identify and remove footers.
-   *
-   * Uses spec-compliant /Artifact tags when available (100% accuracy), or
-   * falls back to heuristic analysis of the bottom 15% of pages.
-   *
-   * @param threshold - Fraction of pages (0.0-1.0) where text must repeat (heuristic mode)
-   */
-  removeFooters(threshold: number): number;
-  /**
-   * Identify and remove headers.
-   *
-   * Uses spec-compliant /Artifact tags when available (100% accuracy), or
-   * falls back to heuristic analysis of the top 15% of pages.
-   *
-   * @param threshold - Fraction of pages (0.0-1.0) where text must repeat (heuristic mode)
-   */
-  removeHeaders(threshold: number): number;
-  /**
-   * Validate PDF/A compliance. Level: "1b", "2b", etc.
-   */
-  validatePdfA(level: string): any;
-  /**
-   * Erase both header and footer content.
-   *
-   * @param page_index - Zero-based page number
-   */
-  eraseArtifacts(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 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;
-  /**
-   * Convert all pages to Markdown.
-   */
-  toMarkdownAll(detect_headings?: boolean | null, include_images?: boolean | null, include_form_fields?: boolean | null): string;
-  /**
-   * 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 text using OCR (optical character recognition).
-   *
-   * NOTE: OCR is not yet supported in the WebAssembly build due to missing
-   * ONNX Runtime support for the web backend in the current implementation.
-   */
-  extractTextOcr(_page_index: number, _engine?: WasmOcrEngine | null): string;
-  /**
-   * Identify and remove both headers and footers.
-   *
-   * Prioritizes ISO 32000 spec-compliant /Artifact tags, with a heuristic
-   * fallback for untagged PDFs.
-   *
-   * @param threshold - Fraction of pages (0.0-1.0) where text must repeat (heuristic mode)
-   */
-  removeArtifacts(threshold: number): number;
-  /**
-   * Reposition an image on a page.
-   */
-  repositionImage(page_index: number, name: string, x: number, y: number): void;
-  /**
-   * Rotate all pages by the given degrees.
-   */
-  rotateAllPages(degrees: number): 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 CropBox of a page.
-   */
-  setPageCropBox(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;
-  /**
-   * Convert all pages to plain text.
-   */
-  toPlainTextAll(): string;
-  /**
-   * Extract text lines from a page.
-   *
-   * Returns an array of objects with: text, bbox, words (array of Word objects).
-   */
-  extractTextLines(page_index: number, region?: Float32Array | null): any;
-  /**
-   * Check if the document has a structure tree (Tagged PDF).
-   */
-  hasStructureTree(): boolean;
-  /**
-   * Set the MediaBox of a page.
-   */
-  setPageMediaBox(page_index: number, llx: number, lly: number, urx: number, ury: number): void;
-  /**
-   * Clear all pending erase operations for a page.
-   */
-  clearEraseRegions(page_index: number): void;
-  /**
-   * 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;
-  /**
-   * Apply all redactions in the document.
-   */
-  applyAllRedactions(): void;
-  /**
-   * 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;
-  /**
-   * 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;
-  /**
-   * Apply redactions on a page (removes redacted content permanently).
-   */
-  applyPageRedactions(page_index: number): void;
-  /**
-   * Flatten form fields on a specific page.
-   *
-   * @param page_index - Zero-based page number
-   */
-  flattenFormsOnPage(page_index: number): void;
-  /**
-   * Flatten all annotations in the document into page content.
-   */
-  flattenAllAnnotations(): void;
-  /**
-   * Save with encryption and return the resulting PDF as bytes.
-   */
-  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;
-  /**
-   * Flatten annotations on a page into the page content.
-   */
-  flattenPageAnnotations(page_index: number): void;
-  /**
-   * Load a PDF document from raw bytes.
-   *
-   * @param data - PDF file contents as Uint8Array
-   * @param password - Optional password for encrypted PDFs
-   * @throws Error if the PDF is invalid or cannot be parsed
-   */
-  constructor(data: Uint8Array, password?: string | null);
-  /**
-   * Save all edits and return the resulting PDF as bytes.
-   *
-   * @returns Uint8Array containing the modified PDF
-   */
-  save(): 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;
-  /**
-   * Focus extraction on a specific rectangular region of a page (v0.3.14).
-   *
-   * @param page_index - Zero-based page number
-   * @param region - [x, y, width, height] in points
-   */
-  within(page_index: number, region: Float32Array): WasmPdfPageRegion;
-  /**
-   * Check if the document contains XFA form data.
-   *
-   * @returns true if the document has XFA form data
-   */
-  hasXfa(): boolean;
-  /**
-   * 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;
-  /**
-   * Get the PDF version as [major, minor].
-   */
-  version(): Uint8Array;
-  /**
-   * Set the document title.
-   */
-  setTitle(title: string): void;
+    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;
+    /**
+     * Delete a page by index (0-based).
+     */
+    deletePage(index: number): void;
+    /**
+     * Deprecated: Use eraseFooter instead.
+     */
+    editFooter(page_index: number): void;
+    /**
+     * Deprecated: Use eraseHeader instead.
+     */
+    editHeader(page_index: 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 both header and footer content.
+     *
+     * @param page_index - Zero-based page number
+     */
+    eraseArtifacts(page_index: number): void;
+    /**
+     * Erase existing footer content.
+     *
+     * Identifies existing text in the footer area (bottom 15%) and marks it for erasure.
+     *
+     * @param page_index - Zero-based page number
+     */
+    eraseFooter(page_index: number): void;
+    /**
+     * Erase existing header content.
+     *
+     * Identifies existing text in the header area (top 15%) and marks it for erasure.
+     *
+     * @param page_index - Zero-based page number
+     */
+    eraseHeader(page_index: number): 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.
+     *
+     * @param page_index - Zero-based page number
+     * @param region - Optional [x, y, width, height] to filter by
+     */
+    extractChars(page_index: number, region?: Float32Array | null): 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.
+     *
+     * @param page_index - Zero-based page number
+     * @param region - Optional [x, y, width, height] to filter by
+     */
+    extractImages(page_index: number, region?: Float32Array | null): any;
+    /**
+     * Extract only straight lines from a page (v0.3.14).
+     *
+     * Identifies paths that form a single straight line segment.
+     *
+     * @param page_index - Zero-based page number
+     * @param region - Optional [x, y, width, height] to filter by
+     * @returns Array of path objects
+     */
+    extractLines(page_index: number, region?: Float32Array | null): any;
+    /**
+     * Extract complete page text data in a single call.
+     *
+     * Returns `{ spans, chars, page_width, page_height }`.
+     * The `chars` are derived from spans using font-metric widths when available.
+     *
+     * Optional `reading_order`: `"column_aware"` for XY-Cut column detection,
+     * or `"top_to_bottom"` (default).
+     */
+    extractPageText(page_index: number, reading_order?: string | null): any;
+    /**
+     * Extract specific pages to a new PDF (returns bytes).
+     */
+    extractPages(pages: Uint32Array): Uint8Array;
+    /**
+     * Extract vector paths (lines, curves, shapes) from a page.
+     *
+     * @param page_index - Zero-based page number
+     * @param region - Optional [x, y, width, height] to filter by
+     * @returns Array of path objects with bbox, stroke_color, fill_color, etc.
+     */
+    extractPaths(page_index: number, region?: Float32Array | null): any;
+    /**
+     * Extract only rectangles from a page (v0.3.14).
+     *
+     * Identifies paths that form axis-aligned rectangles.
+     *
+     * @param page_index - Zero-based page number
+     * @param region - Optional [x, y, width, height] to filter by
+     * @returns Array of path objects
+     */
+    extractRects(page_index: number, region?: Float32Array | null): 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.
+     *
+     * Optional `reading_order`: `"column_aware"` for XY-Cut column detection,
+     * or `"top_to_bottom"` (default).
+     */
+    extractSpans(page_index: number, region?: Float32Array | null, reading_order?: string | null): any;
+    /**
+     * Extract tables from a page (v0.3.14).
+     *
+     * @param page_index - Zero-based page number
+     * @param region - Optional [x, y, width, height] to filter by
+     */
+    extractTables(page_index: number, region?: Float32Array | null): any;
+    /**
+     * Extract plain text from a single page.
+     *
+     * @param page_index - Zero-based page number
+     * @param region - Optional [x, y, width, height] to filter by
+     */
+    extractText(page_index: number, region: any): string;
+    /**
+     * Extract text lines from a page.
+     *
+     * Returns an array of objects with: text, bbox, words (array of Word objects).
+     */
+    extractTextLines(page_index: number, region?: Float32Array | null): any;
+    /**
+     * Extract text using OCR (optical character recognition).
+     *
+     * NOTE: OCR is not yet supported in the WebAssembly build due to missing
+     * ONNX Runtime support for the web backend in the current implementation.
+     */
+    extractTextOcr(_page_index: number, _engine?: WasmOcrEngine | null): string;
+    /**
+     * Extract word-level data from a page.
+     *
+     * Returns an array of objects with: text, bbox, font_name, font_size,
+     * font_weight, is_italic, is_bold.
+     */
+    extractWords(page_index: number, region?: Float32Array | null): any;
+    /**
+     * 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 - PDF file contents as Uint8Array
+     * @param password - Optional password for encrypted PDFs
+     * @throws Error if the PDF is invalid or cannot be parsed
+     */
+    constructor(data: Uint8Array, password?: string | null);
+    /**
+     * 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;
+    /**
+     * Identify and remove both headers and footers.
+     *
+     * Prioritizes ISO 32000 spec-compliant /Artifact tags, with a heuristic
+     * fallback for untagged PDFs.
+     *
+     * @param threshold - Fraction of pages (0.0-1.0) where text must repeat (heuristic mode)
+     */
+    removeArtifacts(threshold: number): number;
+    /**
+     * Identify and remove footers.
+     *
+     * Uses spec-compliant /Artifact tags when available (100% accuracy), or
+     * falls back to heuristic analysis of the bottom 15% of pages.
+     *
+     * @param threshold - Fraction of pages (0.0-1.0) where text must repeat (heuristic mode)
+     */
+    removeFooters(threshold: number): number;
+    /**
+     * Identify and remove headers.
+     *
+     * Uses spec-compliant /Artifact tags when available (100% accuracy), or
+     * falls back to heuristic analysis of the top 15% of pages.
+     *
+     * @param threshold - Fraction of pages (0.0-1.0) where text must repeat (heuristic mode)
+     */
+    removeHeaders(threshold: 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 all edits and return the resulting PDF as bytes.
+     *
+     * @returns Uint8Array containing the modified PDF
+     */
+    save(): Uint8Array;
+    /**
+     * Save with encryption and return the resulting PDF as bytes.
+     */
+    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 the modified PDF and return as bytes.
+     * `saveToBytes()` is the original method; `save()` is a convenience alias.
+     *
+     * @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: false)
+     */
+    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;
+    /**
+     * Validate PDF/A compliance. Level: "1b", "2b", etc.
+     */
+    validatePdfA(level: string): any;
+    /**
+     * Get the PDF version as [major, minor].
+     */
+    version(): Uint8Array;
+    /**
+     * Focus extraction on a specific rectangular region of a page (v0.3.14).
+     *
+     * @param page_index - Zero-based page number
+     * @param region - [x, y, width, height] in points
+     */
+    within(page_index: number, region: Float32Array): WasmPdfPageRegion;
+    /**
+     * Get XMP metadata from the document.
+     *
+     * @returns Object with XMP fields (dc_title, dc_creator, etc.) or null if no XMP
+     */
+    xmpMetadata(): any;
 }
 
+/**
+ * A focused view of a PDF page region for scoped extraction (v0.3.14).
+ */
 export class WasmPdfPageRegion {
-  private constructor();
-  free(): void;
-  [Symbol.dispose](): void;
-  /**
-   * Extract text from this region.
-   */
-  extractText(): string;
-  /**
-   * Extract character-level data from this region.
-   */
-  extractChars(): any;
-  /**
-   * Extract straight lines from this region.
-   */
-  extractLines(): any;
-  /**
-   * Extract vector paths from this region.
-   */
-  extractPaths(): any;
-  /**
-   * Extract rectangles from this region.
-   */
-  extractRects(): any;
-  /**
-   * Extract words from this region.
-   */
-  extractWords(): any;
-  /**
-   * Extract images from this region.
-   */
-  extractImages(): any;
-  /**
-   * Extract tables from this region.
-   */
-  extractTables(): any;
-  /**
-   * Extract text using OCR from this region.
-   */
-  extractTextOcr(_engine?: WasmOcrEngine | null): string;
-  /**
-   * Extract text lines from this region.
-   */
-  extractTextLines(): any;
+    private constructor();
+    free(): void;
+    [Symbol.dispose](): void;
+    /**
+     * Extract character-level data from this region.
+     */
+    extractChars(): any;
+    /**
+     * Extract images from this region.
+     */
+    extractImages(): any;
+    /**
+     * Extract straight lines from this region.
+     */
+    extractLines(): any;
+    /**
+     * Extract vector paths from this region.
+     */
+    extractPaths(): any;
+    /**
+     * Extract rectangles from this region.
+     */
+    extractRects(): any;
+    /**
+     * Extract tables from this region.
+     */
+    extractTables(): any;
+    /**
+     * Extract text from this region.
+     */
+    extractText(): string;
+    /**
+     * Extract text lines from this region.
+     */
+    extractTextLines(): any;
+    /**
+     * Extract text using OCR from this region.
+     */
+    extractTextOcr(_engine?: WasmOcrEngine | null): string;
+    /**
+     * Extract words from this region.
+     */
+    extractWords(): any;
 }
+
+/**
+ * Disable all pdf_oxide log output — convenience wrapper for
+ * `setLogLevel("off")`.
+ */
+export function disableLogging(): void;
+
+/**
+ * Set the maximum log level for pdf_oxide messages.
+ *
+ * Accepts one of: `"off"`, `"error"`, `"warn"` / `"warning"`, `"info"`,
+ * `"debug"`, `"trace"`. Case-insensitive. Default is `"off"` — the library
+ * is silent unless explicitly enabled.
+ *
+ * Logs are forwarded to the browser console (`console.log`, `console.warn`,
+ * `console.error`, etc.). Fixes issue #280.
+ *
+ * @example
+ * ```javascript
+ * import init, { setLogLevel } from "pdf-oxide-wasm";
+ * await init();
+ * setLogLevel("warn");
+ * ```
+ */
+export function setLogLevel(level: string): void;