@jackgreen2018/pdf-engine 1.0.45 → 1.0.47

package/pkg/pdf_engine.d.ts

@@ -1,16 +1,14 @@
 /* tslint:disable */
 /* eslint-disable */
 
-export function get_page_count(input: Uint8Array): number;
+export function extract_text(buffer: Uint8Array): string;
 
-export function get_pdf_info(input: Uint8Array): any;
+export function get_page_count(buffer: Uint8Array): number;
 
-export function init(): Promise<any>;
+export function get_pdf_info(buffer: Uint8Array): string;
 
-export function merge_pdfs(a: Uint8Array, b: Uint8Array): Uint8Array;
+export function init(): void;
 
-export function merge_pdfs_vec(docs: Array<any>): Uint8Array;
+export function merge(pdf_buffers: Array<any>): Uint8Array;
 
-export function optimize_pdf(input: Uint8Array): Uint8Array;
-
-export function split_pdf(input: Uint8Array, pages: Array<any>): Array<any>;
+export function split(buffer: Uint8Array, pages: Array<any>): Array<any>;

package/pkg/pdf_engine.js

@@ -5,5 +5,5 @@ import { __wbg_set_wasm } from "./pdf_engine_bg.js";
 __wbg_set_wasm(wasm);
 wasm.__wbindgen_start();
 export {
-    get_page_count, get_pdf_info, init, merge_pdfs, merge_pdfs_vec, optimize_pdf, split_pdf
+    extract_text, get_page_count, get_pdf_info, init, merge, split
 } from "./pdf_engine_bg.js";

package/pkg/pdf_engine_bg.js

@@ -1,106 +1,100 @@
 /**
- * @param {Uint8Array} input
- * @returns {number}
+ * @param {Uint8Array} buffer
+ * @returns {string}
  */
-export function get_page_count(input) {
-    const ptr0 = passArray8ToWasm0(input, wasm.__wbindgen_malloc);
-    const len0 = WASM_VECTOR_LEN;
-    const ret = wasm.get_page_count(ptr0, len0);
-    if (ret[2]) {
-        throw takeFromExternrefTable0(ret[1]);
+export function extract_text(buffer) {
+    let deferred3_0;
+    let deferred3_1;
+    try {
+        const ptr0 = passArray8ToWasm0(buffer, wasm.__wbindgen_malloc);
+        const len0 = WASM_VECTOR_LEN;
+        const ret = wasm.extract_text(ptr0, len0);
+        var ptr2 = ret[0];
+        var len2 = ret[1];
+        if (ret[3]) {
+            ptr2 = 0; len2 = 0;
+            throw takeFromExternrefTable0(ret[2]);
+        }
+        deferred3_0 = ptr2;
+        deferred3_1 = len2;
+        return getStringFromWasm0(ptr2, len2);
+    } finally {
+        wasm.__wbindgen_free(deferred3_0, deferred3_1, 1);
     }
-    return ret[0] >>> 0;
 }
 
 /**
- * @param {Uint8Array} input
- * @returns {any}
+ * @param {Uint8Array} buffer
+ * @returns {number}
  */
-export function get_pdf_info(input) {
-    const ptr0 = passArray8ToWasm0(input, wasm.__wbindgen_malloc);
+export function get_page_count(buffer) {
+    const ptr0 = passArray8ToWasm0(buffer, wasm.__wbindgen_malloc);
     const len0 = WASM_VECTOR_LEN;
-    const ret = wasm.get_pdf_info(ptr0, len0);
+    const ret = wasm.get_page_count(ptr0, len0);
     if (ret[2]) {
         throw takeFromExternrefTable0(ret[1]);
     }
-    return takeFromExternrefTable0(ret[0]);
-}
-
-/**
- * @returns {Promise<any>}
- */
-export function init() {
-    const ret = wasm.init();
-    return ret;
+    return ret[0] >>> 0;
 }
 
 /**
- * @param {Uint8Array} a
- * @param {Uint8Array} b
- * @returns {Uint8Array}
+ * @param {Uint8Array} buffer
+ * @returns {string}
  */
-export function merge_pdfs(a, b) {
-    const ptr0 = passArray8ToWasm0(a, wasm.__wbindgen_malloc);
-    const len0 = WASM_VECTOR_LEN;
-    const ptr1 = passArray8ToWasm0(b, wasm.__wbindgen_malloc);
-    const len1 = WASM_VECTOR_LEN;
-    const ret = wasm.merge_pdfs(ptr0, len0, ptr1, len1);
-    if (ret[3]) {
-        throw takeFromExternrefTable0(ret[2]);
+export function get_pdf_info(buffer) {
+    let deferred3_0;
+    let deferred3_1;
+    try {
+        const ptr0 = passArray8ToWasm0(buffer, wasm.__wbindgen_malloc);
+        const len0 = WASM_VECTOR_LEN;
+        const ret = wasm.get_pdf_info(ptr0, len0);
+        var ptr2 = ret[0];
+        var len2 = ret[1];
+        if (ret[3]) {
+            ptr2 = 0; len2 = 0;
+            throw takeFromExternrefTable0(ret[2]);
+        }
+        deferred3_0 = ptr2;
+        deferred3_1 = len2;
+        return getStringFromWasm0(ptr2, len2);
+    } finally {
+        wasm.__wbindgen_free(deferred3_0, deferred3_1, 1);
     }
-    var v3 = getArrayU8FromWasm0(ret[0], ret[1]).slice();
-    wasm.__wbindgen_free(ret[0], ret[1] * 1, 1);
-    return v3;
 }
 
-/**
- * @param {Array<any>} docs
- * @returns {Uint8Array}
- */
-export function merge_pdfs_vec(docs) {
-    const ret = wasm.merge_pdfs_vec(docs);
-    if (ret[3]) {
-        throw takeFromExternrefTable0(ret[2]);
+export function init() {
+    const ret = wasm.init();
+    if (ret[1]) {
+        throw takeFromExternrefTable0(ret[0]);
     }
-    var v1 = getArrayU8FromWasm0(ret[0], ret[1]).slice();
-    wasm.__wbindgen_free(ret[0], ret[1] * 1, 1);
-    return v1;
 }
 
 /**
- * @param {Uint8Array} input
+ * @param {Array<any>} pdf_buffers
  * @returns {Uint8Array}
  */
-export function optimize_pdf(input) {
-    const ptr0 = passArray8ToWasm0(input, wasm.__wbindgen_malloc);
-    const len0 = WASM_VECTOR_LEN;
-    const ret = wasm.optimize_pdf(ptr0, len0);
-    if (ret[3]) {
-        throw takeFromExternrefTable0(ret[2]);
+export function merge(pdf_buffers) {
+    const ret = wasm.merge(pdf_buffers);
+    if (ret[2]) {
+        throw takeFromExternrefTable0(ret[1]);
     }
-    var v2 = getArrayU8FromWasm0(ret[0], ret[1]).slice();
-    wasm.__wbindgen_free(ret[0], ret[1] * 1, 1);
-    return v2;
+    return takeFromExternrefTable0(ret[0]);
 }
 
 /**
- * @param {Uint8Array} input
+ * @param {Uint8Array} buffer
  * @param {Array<any>} pages
  * @returns {Array<any>}
  */
-export function split_pdf(input, pages) {
-    const ptr0 = passArray8ToWasm0(input, wasm.__wbindgen_malloc);
+export function split(buffer, pages) {
+    const ptr0 = passArray8ToWasm0(buffer, wasm.__wbindgen_malloc);
     const len0 = WASM_VECTOR_LEN;
-    const ret = wasm.split_pdf(ptr0, len0, pages);
+    const ret = wasm.split(ptr0, len0, pages);
     if (ret[2]) {
         throw takeFromExternrefTable0(ret[1]);
     }
     return takeFromExternrefTable0(ret[0]);
 }
-export function __wbg_Error_92b29b0548f8b746(arg0, arg1) {
-    const ret = Error(getStringFromWasm0(arg0, arg1));
-    return ret;
-}
 export function __wbg___wbindgen_number_get_394265ed1e1b84ee(arg0, arg1) {
     const obj = arg1;
     const ret = typeof(obj) === 'number' ? obj : undefined;
@@ -136,10 +130,6 @@ export function __wbg_new_32b398fb48b6d94a() {
     const ret = new Array();
     return ret;
 }
-export function __wbg_new_7796ffc7ed656783() {
-    const ret = new Map();
-    return ret;
-}
 export function __wbg_new_from_slice_77cdfb7977362f3c(arg0, arg1) {
     const ret = new Uint8Array(getArrayU8FromWasm0(arg0, arg1));
     return ret;
@@ -151,14 +141,6 @@ export function __wbg_push_d2ae3af0c1217ae6(arg0, arg1) {
     const ret = arg0.push(arg1);
     return ret;
 }
-export function __wbg_resolve_2191a4dfe481c25b(arg0) {
-    const ret = Promise.resolve(arg0);
-    return ret;
-}
-export function __wbg_set_575dd786d51585f8(arg0, arg1, arg2) {
-    const ret = arg0.set(arg1, arg2);
-    return ret;
-}
 export function __wbindgen_cast_0000000000000001(arg0, arg1) {
     // Cast intrinsic for `Ref(String) -> Externref`.
     const ret = getStringFromWasm0(arg0, arg1);

package/pkg/pdf_engine_bg.wasm.d.ts

@@ -1,13 +1,12 @@
 /* tslint:disable */
 /* eslint-disable */
 export const memory: WebAssembly.Memory;
+export const extract_text: (a: number, b: number) => [number, number, number, number];
 export const get_page_count: (a: number, b: number) => [number, number, number];
-export const get_pdf_info: (a: number, b: number) => [number, number, number];
-export const init: () => any;
-export const merge_pdfs: (a: number, b: number, c: number, d: number) => [number, number, number, number];
-export const merge_pdfs_vec: (a: any) => [number, number, number, number];
-export const optimize_pdf: (a: number, b: number) => [number, number, number, number];
-export const split_pdf: (a: number, b: number, c: any) => [number, number, number];
+export const get_pdf_info: (a: number, b: number) => [number, number, number, number];
+export const init: () => [number, number];
+export const merge: (a: any) => [number, number, number];
+export const split: (a: number, b: number, c: any) => [number, number, number];
 export const __wbindgen_externrefs: WebAssembly.Table;
 export const __wbindgen_malloc: (a: number, b: number) => number;
 export const __externref_table_dealloc: (a: number) => void;

package/src/cli.ts

@@ -0,0 +1,66 @@
+#!/usr/bin/env node
+import { createRequire } from 'module';
+import pdfEngine from './index.js';
+const require = createRequire(import.meta.url);
+
+const USAGE = `pdf-engine — Rust/WASM PDF processing (v${require('../package.json').version})
+
+Usage:
+  pdf-engine <command> [args]
+
+Commands:
+  page-count <file>           Print the page count of a PDF
+  extract-text <file>         Extract text from a PDF
+  merge <file1> <file2> ...  Merge PDFs into a single output
+  split <file> <page1> ...   Split a PDF by 0-based page indices
+  help                       Print this message
+`;
+
+async function main(): Promise<number> {
+  const [cmd, ...args] = process.argv.slice(2);
+  if (!cmd || cmd === '-h' || cmd === '--help' || cmd === 'help') {
+    process.stdout.write(USAGE);
+    return 0;
+  }
+  const fs = await import('fs/promises');
+  const read = async (p: string) => new Uint8Array(await fs.readFile(p));
+  await pdfEngine.init();
+  switch (cmd) {
+    case 'page-count': {
+      const n = await pdfEngine.getPageCount(await read(args[0]));
+      process.stdout.write(String(n) + '\n');
+      return 0;
+    }
+    case 'extract-text': {
+      const t = await pdfEngine.extractText(await read(args[0]));
+      process.stdout.write(t + '\n');
+      return 0;
+    }
+    case 'merge': {
+      const out = await pdfEngine.merge(await Promise.all(args.map(read)));
+      await fs.writeFile('merged.pdf', out);
+      process.stdout.write(`wrote merged.pdf (${out.byteLength} bytes)\n`);
+      return 0;
+    }
+    case 'split': {
+      const [file, ...pages] = args;
+      const out = await pdfEngine.split(
+        await read(file),
+        pages.map(Number),
+      );
+      for (let i = 0; i < out.length; i++) {
+        await fs.writeFile(`part-${i}.pdf`, out[i]);
+      }
+      process.stdout.write(`wrote ${out.length} part-*.pdf files\n`);
+      return 0;
+    }
+    default:
+      process.stderr.write(`unknown command: ${cmd}\n${USAGE}`);
+      return 1;
+  }
+}
+
+main().then((c) => process.exit(c)).catch((e) => {
+  process.stderr.write(String(e) + '\n');
+  process.exit(1);
+});

package/src/index.ts

@@ -0,0 +1,62 @@
+// PDF Engine TypeScript bindings for Rust/WASM PDF processing library
+
+import * as wasm from '../pkg/pdf_engine.js';
+
+export async function initialize(): Promise<void> {
+    await wasm.init();
+}
+
+export async function getPageCount(buffer: Uint8Array): Promise<number> {
+    return await wasm.get_page_count(buffer);
+}
+
+export async function extractText(buffer: Uint8Array): Promise<string> {
+    return await wasm.extract_text(buffer);
+}
+
+export async function merge(pdfBuffers: Uint8Array[]): Promise<Uint8Array> {
+    const result = await wasm.merge(pdfBuffers);
+    return result;
+}
+
+export async function split(buffer: Uint8Array, pages: number[]): Promise<Uint8Array[]> {
+    const resultArray = await wasm.split(buffer, pages);
+    return Array.from(resultArray).map(arr => arr as Uint8Array);
+}
+
+export class PdfEngineImpl {
+    constructor() {
+        this.initialized = false;
+    }
+    private initialized = false;
+
+    async init(): Promise<void> {
+        if (!this.initialized) {
+            await initialize();
+            this.initialized = true;
+        }
+    }
+
+    async getPageCount(buffer: Uint8Array): Promise<number> {
+        await this.init();
+        return await getPageCount(buffer);
+    }
+
+    async extractText(buffer: Uint8Array): Promise<string> {
+        await this.init();
+        return await extractText(buffer);
+    }
+
+    async merge(pdfBuffers: Uint8Array[]): Promise<Uint8Array> {
+        await this.init();
+        return await merge(pdfBuffers);
+    }
+
+    async split(buffer: Uint8Array, pages: number[]): Promise<Uint8Array[]> {
+        await this.init();
+        return await split(buffer, pages);
+    }
+}
+
+const pdfEngine = new PdfEngineImpl();
+export default pdfEngine;

package/src/lib.rs

@@ -0,0 +1,294 @@
+use wasm_bindgen::prelude::*;
+use js_sys::{Array, Uint8Array};
+use lopdf::{Document, Object, ObjectId};
+use std::collections::BTreeMap;
+
+#[wasm_bindgen]
+pub fn init() -> Result<(), JsValue> {
+    Ok(())
+}
+
+#[wasm_bindgen]
+pub fn get_page_count(buffer: &[u8]) -> Result<u32, JsValue> {
+    let doc = Document::load_mem(buffer)
+        .map_err(|e| JsValue::from_str(&format!("PDF error: {}", e)))?;
+    Ok(doc.get_pages().len().max(1) as u32)
+}
+
+/// Decode PDF hex strings (<HHHH...>) in content stream operators.
+fn decode_hex_strings(content: &str) -> String {
+    let mut result = String::new();
+    let bytes = content.as_bytes();
+    let mut i = 0;
+    while i < bytes.len() {
+        if bytes[i] == b'<' {
+            let mut j = i + 1;
+            while j < bytes.len() && bytes[j] != b'>' {
+                j += 1;
+            }
+            if j > i + 1 && j < bytes.len() {
+                let hex = &content[i+1..j];
+                if hex.len() % 2 == 0 && hex.chars().all(|c| c.is_ascii_hexdigit()) {
+                    let mut buf = Vec::with_capacity(hex.len() / 2);
+                    for k in (0..hex.len()).step_by(2) {
+                        if let Ok(byte) = u8::from_str_radix(&hex[k..k+2], 16) {
+                            buf.push(byte);
+                        }
+                    }
+                    if let Ok(s) = String::from_utf8(buf) {
+                        result.push_str(&s);
+                    }
+                }
+            }
+            i = j + 1;
+        } else {
+            i += 1;
+        }
+    }
+    result
+}
+
+/// Extract text from all content streams by decoding hex strings.
+///
+/// Scans every decompressed stream for <HEX> patterns and decodes them,
+/// bypassing the BT/ET block requirement.
+fn collect_page_text(doc: &Document) -> String {
+    let mut text = String::new();
+
+    for (_id, obj) in doc.objects.iter() {
+        let Object::Stream(ref stream) = obj else { continue };
+        let mut s = stream.clone();
+        let _ = s.decompress();
+        let content = String::from_utf8_lossy(&s.content);
+        if content.is_empty() {
+            continue;
+        }
+
+        let decoded = decode_hex_strings(&content);
+        if !decoded.is_empty() {
+            if !text.is_empty() {
+                text.push('\n');
+            }
+            text.push_str(&decoded);
+        }
+    }
+
+    text
+}
+
+#[wasm_bindgen]
+pub fn extract_text(buffer: &[u8]) -> Result<String, JsValue> {
+    let doc = Document::load_mem(buffer)
+        .map_err(|e| JsValue::from_str(&format!("PDF error: {}", e)))?;
+
+    let text = collect_page_text(&doc);
+
+    if text.is_empty() {
+        Ok("No text extracted.".to_string())
+    } else {
+        Ok(text)
+    }
+}
+
+/// Remap all ObjectId references in `obj` using `id_map`.
+fn remap_refs(obj: &mut Object, id_map: &BTreeMap<ObjectId, ObjectId>) {
+    match obj {
+        Object::Reference(r) => {
+            if let Some(&new_id) = id_map.get(r) {
+                *r = new_id;
+            }
+        }
+        Object::Array(arr) => {
+            for item in arr {
+                remap_refs(item, id_map);
+            }
+        }
+        Object::Dictionary(dict) => {
+            for (_, v) in dict.iter_mut() {
+                remap_refs(v, id_map);
+            }
+        }
+        Object::Stream(stream) => {
+            for (_, v) in stream.dict.iter_mut() {
+                remap_refs(v, id_map);
+            }
+        }
+        _ => {}
+    }
+}
+
+/// Collect all object IDs reachable from `start` in `doc` (including start itself).
+fn collect_reachable(start: ObjectId, doc: &Document, visited: &mut BTreeMap<ObjectId, Object>) {
+    if visited.contains_key(&start) {
+        return;
+    }
+    if let Ok(obj) = doc.get_object(start) {
+        visited.insert(start, obj.clone());
+        walk_refs(&obj, doc, visited);
+    }
+}
+
+/// Walk all references in `obj` and collect reachable objects.
+fn walk_refs(obj: &Object, doc: &Document, visited: &mut BTreeMap<ObjectId, Object>) {
+    match obj {
+        Object::Reference(r) => collect_reachable(*r, doc, visited),
+        Object::Array(arr) => {
+            for item in arr {
+                walk_refs(item, doc, visited);
+            }
+        }
+        Object::Dictionary(dict) => {
+            for (_, v) in dict.iter() {
+                walk_refs(v, doc, visited);
+            }
+        }
+        Object::Stream(stream) => {
+            for (_, v) in stream.dict.iter() {
+                walk_refs(v, doc, visited);
+            }
+        }
+        _ => {}
+    }
+}
+
+/// Copy page at `page_obj_id` from `src` into `dst`, updating all internal references.
+fn copy_page_into(src: &Document, dst: &mut Document, page_obj_id: ObjectId) -> ObjectId {
+    let mut to_copy: BTreeMap<ObjectId, Object> = BTreeMap::new();
+    collect_reachable(page_obj_id, src, &mut to_copy);
+
+    let mut id_map: BTreeMap<ObjectId, ObjectId> = BTreeMap::new();
+    let mut next_id = dst.max_id + 1;
+
+    let mut ids_sorted: Vec<ObjectId> = to_copy.keys().cloned().collect();
+    ids_sorted.sort_by_key(|(x, _)| *x);
+
+    for old_id in ids_sorted {
+        let new_id = loop {
+            let candidate = (next_id, 0);
+            if !dst.objects.contains_key(&candidate) {
+                break candidate;
+            }
+            next_id += 1;
+        };
+        id_map.insert(old_id, new_id);
+        let mut obj = to_copy[&old_id].clone();
+        remap_refs(&mut obj, &id_map);
+        dst.objects.insert(new_id, obj);
+        dst.max_id = next_id.max(dst.max_id);
+    }
+
+    *id_map.get(&page_obj_id).unwrap_or(&(0, 0))
+}
+
+#[wasm_bindgen]
+pub fn merge(pdf_buffers: Array) -> Result<Uint8Array, JsValue> {
+    let len = pdf_buffers.length();
+    if len == 0 {
+        return Ok(Uint8Array::new_from_slice(&[]));
+    }
+
+    let first_buf = pdf_buffers.get(0).dyn_into::<Uint8Array>()
+        .map_err(|_| JsValue::from_str("merge: first item not Uint8Array"))?;
+    let mut doc = Document::load_mem(&first_buf.to_vec())
+        .map_err(|e| JsValue::from_str(&format!("PDF load error: {}", e)))?;
+
+    for i in 1..len {
+        let buf = pdf_buffers.get(i).dyn_into::<Uint8Array>()
+            .map_err(|_| JsValue::from_str("merge: item not Uint8Array"))?;
+        let other = Document::load_mem(&buf.to_vec())
+            .map_err(|e| JsValue::from_str(&format!("PDF load error: {}", e)))?;
+
+        let page_count = doc.get_pages().len() as i64;
+
+        for &page_obj_id in other.get_pages().values() {
+            let new_page_id = copy_page_into(&other, &mut doc, page_obj_id);
+            if let Ok(root_ref) = doc.trailer.get(b"Root").and_then(|r| r.as_reference()) {
+                if let Some(Object::Dictionary(ref mut root_dict)) = doc.objects.get_mut(&root_ref) {
+                    if let Ok(pages_ref) = root_dict.get(b"Pages").and_then(|p| p.as_reference()) {
+                        if let Some(Object::Dictionary(ref mut pages_dict)) = doc.objects.get_mut(&pages_ref) {
+                            if let Ok(kids) = pages_dict.get_mut(b"Kids") {
+                                if let Object::Array(ref mut kids_arr) = kids {
+                                    kids_arr.push(Object::Reference(new_page_id));
+                                }
+                            }
+                            if let Ok(count) = pages_dict.get_mut(b"Count") {
+                                *count = Object::Integer(page_count + 1);
+                            }
+                        }
+                    }
+                }
+            }
+        }
+    }
+
+    let mut buf = Vec::new();
+    doc.save_to(&mut buf).map_err(|e| JsValue::from_str(&format!("PDF save error: {}", e)))?;
+    Ok(Uint8Array::new_from_slice(&buf))
+}
+
+#[wasm_bindgen]
+pub fn split(buffer: &[u8], pages: Array) -> Result<Array, JsValue> {
+    let doc = Document::load_mem(buffer)
+        .map_err(|e| JsValue::from_str(&format!("PDF error: {}", e)))?;
+    let page_len = pages.length();
+
+    let page_map: BTreeMap<u32, ObjectId> = doc.get_pages();
+    let results = Array::new();
+
+    for i in 0..page_len {
+        let page_num = pages.get(i).as_f64().unwrap_or(0.0) as u32;
+        // PDF page numbers are 1-based internally
+        let Some(&page_obj_id) = page_map.get(&(page_num + 1)) else { continue };
+
+        let mut new_doc = Document::with_version("1.5");
+        let new_page_id = copy_page_into(&doc, &mut new_doc, page_obj_id);
+
+        // Build the page tree: Pages -> [page], Catalog -> Pages
+        let pages_id = (new_doc.max_id + 1, 0);
+        let catalog_id = (new_doc.max_id + 2, 0);
+
+        let pages_dict = lopdf::dictionary! {
+            "Type" => "Pages",
+            "Kids" => vec![Object::Reference(new_page_id)],
+            "Count" => 1
+        };
+        new_doc.objects.insert(pages_id, Object::Dictionary(pages_dict));
+        new_doc.max_id = pages_id.0.max(new_doc.max_id);
+
+        let catalog_dict = lopdf::dictionary! {
+            "Type" => "Catalog",
+            "Pages" => Object::Reference(pages_id)
+        };
+        new_doc.objects.insert(catalog_id, Object::Dictionary(catalog_dict));
+        new_doc.max_id = catalog_id.0.max(new_doc.max_id);
+        new_doc.trailer.set("Root", Object::Reference(catalog_id));
+
+        let mut pdf_bytes = Vec::new();
+        let _ = new_doc.save_to(&mut pdf_bytes);
+        results.push(&Uint8Array::new_from_slice(&pdf_bytes).into());
+    }
+
+    if results.length() == 0 {
+        results.push(&Uint8Array::new_from_slice(&[]).into());
+    }
+
+    Ok(results)
+}
+
+#[wasm_bindgen]
+pub fn get_pdf_info(buffer: &[u8]) -> Result<String, JsValue> {
+    let count = get_page_count(buffer)?;
+    Ok(format!("PDF with {} pages", count))
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn page_count_of_empty_doc_is_one() {
+        // ponytail: lopdf get_pages() returns empty map for docs with no pages
+        let doc = Document::with_version("1.5");
+        assert_eq!(doc.get_pages().len().max(1), 1);
+    }
+}

package/LICENSE

@@ -1,21 +0,0 @@
-MIT License
-
-Copyright (c) 2024 Jack Green
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.