pdf-oxide-wasm 0.3.13 → 0.3.15

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pdf-oxide-wasm",
-  "version": "0.3.13",
+  "version": "0.3.15",
   "description": "Fast, zero-dependency PDF toolkit for Node.js, browsers, and edge runtimes — text extraction, markdown/HTML conversion, search, form filling, creation, and editing. Rust core compiled to WebAssembly.",
   "license": "MIT OR Apache-2.0",
   "repository": {

package/pdf_oxide.d.ts

@@ -1,6 +1,86 @@
 /* tslint:disable */
 /* eslint-disable */
 
+/**
+ * Style configuration for header/footer text.
+ */
+export class ArtifactStyle {
+    free(): void;
+    [Symbol.dispose](): void;
+    bold(): ArtifactStyle;
+    color(r: number, g: number, b: number): ArtifactStyle;
+    font(name: string, size: number): ArtifactStyle;
+    constructor();
+}
+
+/**
+ * A header or footer artifact definition.
+ */
+export class WasmArtifact {
+    free(): void;
+    [Symbol.dispose](): void;
+    static center(text: string): WasmArtifact;
+    static left(text: string): WasmArtifact;
+    constructor();
+    static right(text: string): WasmArtifact;
+    withOffset(offset: number): WasmArtifact;
+    withStyle(style: ArtifactStyle): WasmArtifact;
+}
+
+/**
+ * A footer definition.
+ */
+export class WasmFooter {
+    free(): void;
+    [Symbol.dispose](): void;
+    static center(text: string): WasmFooter;
+    static left(text: string): WasmFooter;
+    constructor();
+    static right(text: string): WasmFooter;
+}
+
+/**
+ * A header definition.
+ */
+export class WasmHeader {
+    free(): void;
+    [Symbol.dispose](): void;
+    static center(text: string): WasmHeader;
+    static left(text: string): WasmHeader;
+    constructor();
+    static right(text: string): WasmHeader;
+}
+
+/**
+ * OCR configuration for WebAssembly.
+ */
+export class WasmOcrConfig {
+    free(): void;
+    [Symbol.dispose](): void;
+    constructor();
+}
+
+/**
+ * OCR engine for WebAssembly.
+ */
+export class WasmOcrEngine {
+    free(): void;
+    [Symbol.dispose](): void;
+    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;
+    footer(footer: WasmArtifact): WasmPageTemplate;
+    header(header: WasmArtifact): WasmPageTemplate;
+    constructor();
+    skipFirstPage(): WasmPageTemplate;
+}
+
 /**
  * Create new PDF documents from Markdown, HTML, or plain text.
  *
@@ -101,6 +181,28 @@ export class WasmPdfDocument {
      * @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.
      */
@@ -128,8 +230,11 @@ export class WasmPdfDocument {
      *
      * 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): any;
+    extractChars(page_index: number, region?: Float32Array | null): any;
     /**
      * Extract image bytes from a page as PNG data.
      *
@@ -141,28 +246,80 @@ export class WasmPdfDocument {
      *
      * 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
      */
-    extractImages(page_index: number): any;
+    extractLines(page_index: number, region?: Float32Array | null): any;
     /**
      * 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): any;
+    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): any;
+    extractSpans(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;
     /**
      * 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?: Float32Array | null): 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.
      */
-    extractText(page_index: number): string;
+    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.
      */
@@ -271,6 +428,33 @@ export class WasmPdfDocument {
      * 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.
      */
@@ -289,13 +473,6 @@ export class WasmPdfDocument {
     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;
     /**
@@ -395,6 +572,13 @@ export class WasmPdfDocument {
      * 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.
      *
@@ -402,3 +586,52 @@ export class WasmPdfDocument {
      */
     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 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;
+}