html-to-markdown-wasm 2.8.0 → 2.8.2

package/dist-node/html_to_markdown_wasm.js

@@ -222,88 +222,90 @@ function getArrayJsValueFromWasm0(ptr, len) {
     return result;
 }
 /**
- * @param {Uint8Array} html
  * @param {any} options
- * @returns {string}
+ * @returns {WasmConversionOptionsHandle}
  */
-exports.convertBytes = function(html, options) {
-    let deferred2_0;
-    let deferred2_1;
+exports.createConversionOptionsHandle = function(options) {
     try {
         const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
-        wasm.convertBytes(retptr, addHeapObject(html), addHeapObject(options));
+        wasm.createConversionOptionsHandle(retptr, addHeapObject(options));
         var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
         var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
         var r2 = getDataViewMemory0().getInt32(retptr + 4 * 2, true);
-        var r3 = getDataViewMemory0().getInt32(retptr + 4 * 3, true);
-        var ptr1 = r0;
-        var len1 = r1;
-        if (r3) {
-            ptr1 = 0; len1 = 0;
-            throw takeObject(r2);
+        if (r2) {
+            throw takeObject(r1);
         }
-        deferred2_0 = ptr1;
-        deferred2_1 = len1;
-        return getStringFromWasm0(ptr1, len1);
+        return WasmConversionOptionsHandle.__wrap(r0);
     } finally {
         wasm.__wbindgen_add_to_stack_pointer(16);
-        wasm.__wbindgen_export4(deferred2_0, deferred2_1, 1);
     }
 };
 
+function _assertClass(instance, klass) {
+    if (!(instance instanceof klass)) {
+        throw new Error(`expected instance of ${klass.name}`);
+    }
+}
 /**
- * Convert HTML to Markdown
- *
- * # Arguments
- *
- * * `html` - The HTML string to convert
- * * `options` - Optional conversion options (as a JavaScript object)
- *
- * # Example
- *
- * ```javascript
- * import { convert } from 'html-to-markdown-wasm';
- *
- * const html = '<h1>Hello World</h1>';
- * const markdown = convert(html);
- * console.log(markdown); // # Hello World
- * ```
  * @param {string} html
  * @param {any} options
- * @returns {string}
+ * @param {WasmInlineImageConfig | null} [image_config]
+ * @returns {WasmHtmlExtraction}
  */
-exports.convert = function(html, options) {
-    let deferred3_0;
-    let deferred3_1;
+exports.convertWithInlineImages = function(html, options, image_config) {
     try {
         const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
         const ptr0 = passStringToWasm0(html, wasm.__wbindgen_export, wasm.__wbindgen_export2);
         const len0 = WASM_VECTOR_LEN;
-        wasm.convert(retptr, ptr0, len0, addHeapObject(options));
+        let ptr1 = 0;
+        if (!isLikeNone(image_config)) {
+            _assertClass(image_config, WasmInlineImageConfig);
+            ptr1 = image_config.__destroy_into_raw();
+        }
+        wasm.convertWithInlineImages(retptr, ptr0, len0, addHeapObject(options), ptr1);
+        var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
+        var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
+        var r2 = getDataViewMemory0().getInt32(retptr + 4 * 2, true);
+        if (r2) {
+            throw takeObject(r1);
+        }
+        return WasmHtmlExtraction.__wrap(r0);
+    } finally {
+        wasm.__wbindgen_add_to_stack_pointer(16);
+    }
+};
+
+/**
+ * @param {Uint8Array} html
+ * @param {WasmConversionOptionsHandle} handle
+ * @returns {string}
+ */
+exports.convertBytesWithOptionsHandle = function(html, handle) {
+    let deferred2_0;
+    let deferred2_1;
+    try {
+        const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+        _assertClass(handle, WasmConversionOptionsHandle);
+        wasm.convertBytesWithOptionsHandle(retptr, addHeapObject(html), handle.__wbg_ptr);
         var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
         var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
         var r2 = getDataViewMemory0().getInt32(retptr + 4 * 2, true);
         var r3 = getDataViewMemory0().getInt32(retptr + 4 * 3, true);
-        var ptr2 = r0;
-        var len2 = r1;
+        var ptr1 = r0;
+        var len1 = r1;
         if (r3) {
-            ptr2 = 0; len2 = 0;
+            ptr1 = 0; len1 = 0;
             throw takeObject(r2);
         }
-        deferred3_0 = ptr2;
-        deferred3_1 = len2;
-        return getStringFromWasm0(ptr2, len2);
+        deferred2_0 = ptr1;
+        deferred2_1 = len1;
+        return getStringFromWasm0(ptr1, len1);
     } finally {
         wasm.__wbindgen_add_to_stack_pointer(16);
-        wasm.__wbindgen_export4(deferred3_0, deferred3_1, 1);
+        wasm.__wbindgen_export4(deferred2_0, deferred2_1, 1);
     }
 };
 
-function _assertClass(instance, klass) {
-    if (!(instance instanceof klass)) {
-        throw new Error(`expected instance of ${klass.name}`);
-    }
-}
 /**
  * @param {string} html
  * @param {WasmConversionOptionsHandle} handle
@@ -337,108 +339,99 @@ exports.convertWithOptionsHandle = function(html, handle) {
     }
 };
 
-/**
- * Initialize panic hook for better error messages in the browser
- */
-exports.init = function() {
-    wasm.init();
-};
-
 /**
  * @param {Uint8Array} html
  * @param {any} options
- * @param {WasmInlineImageConfig | null} [image_config]
- * @returns {WasmHtmlExtraction}
+ * @returns {string}
  */
-exports.convertBytesWithInlineImages = function(html, options, image_config) {
+exports.convertBytes = function(html, options) {
+    let deferred2_0;
+    let deferred2_1;
     try {
         const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
-        let ptr0 = 0;
-        if (!isLikeNone(image_config)) {
-            _assertClass(image_config, WasmInlineImageConfig);
-            ptr0 = image_config.__destroy_into_raw();
-        }
-        wasm.convertBytesWithInlineImages(retptr, addHeapObject(html), addHeapObject(options), ptr0);
+        wasm.convertBytes(retptr, addHeapObject(html), addHeapObject(options));
         var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
         var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
         var r2 = getDataViewMemory0().getInt32(retptr + 4 * 2, true);
-        if (r2) {
-            throw takeObject(r1);
+        var r3 = getDataViewMemory0().getInt32(retptr + 4 * 3, true);
+        var ptr1 = r0;
+        var len1 = r1;
+        if (r3) {
+            ptr1 = 0; len1 = 0;
+            throw takeObject(r2);
         }
-        return WasmHtmlExtraction.__wrap(r0);
+        deferred2_0 = ptr1;
+        deferred2_1 = len1;
+        return getStringFromWasm0(ptr1, len1);
     } finally {
         wasm.__wbindgen_add_to_stack_pointer(16);
+        wasm.__wbindgen_export4(deferred2_0, deferred2_1, 1);
     }
 };
 
 /**
+ * Convert HTML to Markdown
+ *
+ * # Arguments
+ *
+ * * `html` - The HTML string to convert
+ * * `options` - Optional conversion options (as a JavaScript object)
+ *
+ * # Example
+ *
+ * ```javascript
+ * import { convert } from 'html-to-markdown-wasm';
+ *
+ * const html = '<h1>Hello World</h1>';
+ * const markdown = convert(html);
+ * console.log(markdown); // # Hello World
+ * ```
+ * @param {string} html
  * @param {any} options
- * @returns {WasmConversionOptionsHandle}
- */
-exports.createConversionOptionsHandle = function(options) {
-    try {
-        const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
-        wasm.createConversionOptionsHandle(retptr, addHeapObject(options));
-        var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
-        var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
-        var r2 = getDataViewMemory0().getInt32(retptr + 4 * 2, true);
-        if (r2) {
-            throw takeObject(r1);
-        }
-        return WasmConversionOptionsHandle.__wrap(r0);
-    } finally {
-        wasm.__wbindgen_add_to_stack_pointer(16);
-    }
-};
-
-/**
- * @param {Uint8Array} html
- * @param {WasmConversionOptionsHandle} handle
  * @returns {string}
  */
-exports.convertBytesWithOptionsHandle = function(html, handle) {
-    let deferred2_0;
-    let deferred2_1;
+exports.convert = function(html, options) {
+    let deferred3_0;
+    let deferred3_1;
     try {
         const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
-        _assertClass(handle, WasmConversionOptionsHandle);
-        wasm.convertBytesWithOptionsHandle(retptr, addHeapObject(html), handle.__wbg_ptr);
+        const ptr0 = passStringToWasm0(html, wasm.__wbindgen_export, wasm.__wbindgen_export2);
+        const len0 = WASM_VECTOR_LEN;
+        wasm.convert(retptr, ptr0, len0, addHeapObject(options));
         var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
         var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
         var r2 = getDataViewMemory0().getInt32(retptr + 4 * 2, true);
         var r3 = getDataViewMemory0().getInt32(retptr + 4 * 3, true);
-        var ptr1 = r0;
-        var len1 = r1;
+        var ptr2 = r0;
+        var len2 = r1;
         if (r3) {
-            ptr1 = 0; len1 = 0;
+            ptr2 = 0; len2 = 0;
             throw takeObject(r2);
         }
-        deferred2_0 = ptr1;
-        deferred2_1 = len1;
-        return getStringFromWasm0(ptr1, len1);
+        deferred3_0 = ptr2;
+        deferred3_1 = len2;
+        return getStringFromWasm0(ptr2, len2);
     } finally {
         wasm.__wbindgen_add_to_stack_pointer(16);
-        wasm.__wbindgen_export4(deferred2_0, deferred2_1, 1);
+        wasm.__wbindgen_export4(deferred3_0, deferred3_1, 1);
     }
 };
 
 /**
- * @param {string} html
+ * @param {Uint8Array} html
  * @param {any} options
  * @param {WasmInlineImageConfig | null} [image_config]
  * @returns {WasmHtmlExtraction}
  */
-exports.convertWithInlineImages = function(html, options, image_config) {
+exports.convertBytesWithInlineImages = function(html, options, image_config) {
     try {
         const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
-        const ptr0 = passStringToWasm0(html, wasm.__wbindgen_export, wasm.__wbindgen_export2);
-        const len0 = WASM_VECTOR_LEN;
-        let ptr1 = 0;
+        let ptr0 = 0;
         if (!isLikeNone(image_config)) {
             _assertClass(image_config, WasmInlineImageConfig);
-            ptr1 = image_config.__destroy_into_raw();
+            ptr0 = image_config.__destroy_into_raw();
         }
-        wasm.convertWithInlineImages(retptr, ptr0, len0, addHeapObject(options), ptr1);
+        wasm.convertBytesWithInlineImages(retptr, addHeapObject(html), addHeapObject(options), ptr0);
         var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
         var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
         var r2 = getDataViewMemory0().getInt32(retptr + 4 * 2, true);
@@ -451,6 +444,13 @@ exports.convertWithInlineImages = function(html, options, image_config) {
     }
 };
 
+/**
+ * Initialize panic hook for better error messages in the browser
+ */
+exports.init = function() {
+    wasm.init();
+};
+
 const WasmConversionOptionsHandleFinalization = (typeof FinalizationRegistry === 'undefined')
     ? { register: () => {}, unregister: () => {} }
     : new FinalizationRegistry(ptr => wasm.__wbg_wasmconversionoptionshandle_free(ptr >>> 0, 1));

package/dist-node/package.json

@@ -3,7 +3,7 @@
   "collaborators": [
     "Na'aman Hirschfeld <nhirschfeld@gmail.com>"
   ],
-  "version": "2.8.0",
+  "version": "2.8.2",
   "license": "MIT",
   "repository": {
     "type": "git",

package/dist-web/README.md

@@ -1,6 +1,6 @@
 # html-to-markdown
 
-High-performance HTML → Markdown conversion powered by Rust. Shipping as a Rust crate, Python package, PHP extension, Ruby gem, Node.js bindings, WebAssembly, and standalone CLI with identical rendering behaviour.
+High-performance HTML → Markdown conversion powered by Rust. Shipping as a Rust crate, Python package, PHP extension, Ruby gem, Elixir Rustler NIF, Node.js bindings, WebAssembly, and standalone CLI with identical rendering behaviour.
 
 [![Crates.io](https://img.shields.io/crates/v/html-to-markdown.svg)](https://crates.io/crates/html-to-markdown)
 [![npm (node)](https://badge.fury.io/js/html-to-markdown-node.svg)](https://www.npmjs.com/package/html-to-markdown-node)
@@ -8,6 +8,7 @@ High-performance HTML → Markdown conversion powered by Rust. Shipping as a Rus
 [![PyPI](https://badge.fury.io/py/html-to-markdown.svg)](https://pypi.org/project/html-to-markdown/)
 [![Packagist](https://img.shields.io/packagist/v/goldziher/html-to-markdown.svg)](https://packagist.org/packages/goldziher/html-to-markdown)
 [![RubyGems](https://badge.fury.io/rb/html-to-markdown.svg)](https://rubygems.org/gems/html-to-markdown)
+[![Hex.pm](https://img.shields.io/hexpm/v/html_to_markdown.svg)](https://hex.pm/packages/html_to_markdown)
 [![NuGet](https://img.shields.io/nuget/v/HtmlToMarkdown.svg)](https://www.nuget.org/packages/HtmlToMarkdown/)
 [![Maven Central](https://img.shields.io/maven-central/v/io.github.goldziher/html-to-markdown.svg)](https://central.sonatype.com/artifact/io.github.goldziher/html-to-markdown)
 [![Go Reference](https://pkg.go.dev/badge/github.com/Goldziher/html-to-markdown/packages/go/htmltomarkdown.svg)](https://pkg.go.dev/github.com/Goldziher/html-to-markdown/packages/go/htmltomarkdown)
@@ -43,6 +44,7 @@ Experience WebAssembly-powered HTML to Markdown conversion instantly in your bro
     - PHP wrapper package – [PHP README](https://github.com/Goldziher/html-to-markdown/blob/main/packages/php/README.md)
     - PHP extension (PIE) – [Extension README](https://github.com/Goldziher/html-to-markdown/blob/main/packages/php-ext/README.md)
 - **Ruby guide** – [Ruby README](https://github.com/Goldziher/html-to-markdown/blob/main/packages/ruby/README.md)
+- **Elixir guide** – [Elixir README](https://github.com/Goldziher/html-to-markdown/blob/main/packages/elixir/README.md)
 - **Rust guide** – [Rust README](https://github.com/Goldziher/html-to-markdown/blob/main/crates/html-to-markdown/README.md)
 - **Contributing** – [CONTRIBUTING.md](https://github.com/Goldziher/html-to-markdown/blob/main/CONTRIBUTING.md) ⭐ Start here!
 - **Changelog** – [CHANGELOG.md](https://github.com/Goldziher/html-to-markdown/blob/main/CHANGELOG.md)
@@ -57,6 +59,7 @@ Experience WebAssembly-powered HTML to Markdown conversion instantly in your bro
 | **Python** (bindings + CLI) | `pip install html-to-markdown`                                            |
 | **PHP** (extension + helpers) | `pie install goldziher/html-to-markdown`<br>`composer require html-to-markdown/extension` |
 | **Ruby** gem                | `bundle add html-to-markdown` or `gem install html-to-markdown`           |
+| **Elixir** (Rustler NIF)    | `{:html_to_markdown, "~> 2.8"}`                                           |
 | **Rust** crate              | `cargo add html-to-markdown-rs`                                           |
 | Rust CLI                    | `cargo install html-to-markdown-cli`                                      |
 | Homebrew CLI                | `brew tap goldziher/tap`<br>`brew install html-to-markdown`               |
@@ -126,6 +129,15 @@ markdown, inline_images, warnings = convert_with_inline_images(
 )
 ```
 
+### Elixir
+
+```elixir
+{:ok, markdown} = HtmlToMarkdown.convert("<h1>Hello</h1>")
+
+# Keyword options are supported (internally mapped to the Rust ConversionOptions struct)
+HtmlToMarkdown.convert!("<p>Wrap me</p>", wrap: true, wrap_width: 32, preprocessing: %{enabled: true})
+```
+
 ### Rust
 
 ```rust
@@ -178,6 +190,7 @@ Derived directly from `tools/runtime-bench/results/latest.json` (Apple M4, share
 - **Rust now leads throughput**: the fused preprocessing + `parse_owned` pathway pushes the CLI to ~1.7 k ops/sec on the 129 KB lists page and ~31 k ops/sec on the HOCR invoice fixture.
 - **Node.js trails by only a few percent** after the buffer/handle work—~1.3 k ops/sec on the lists fixture and 27 k ops/sec on HOCR invoices without any UTF-16 copies.
 - **Python remains competitive** but now sits below Node/Rust (~4.0 k average ops/sec); stick to the v2 API to avoid the deprecated compatibility shim.
+- **Elixir matches the Rust core** because the Rustler NIF executes the same `ConversionOptions` pipeline—benchmarks land between 170–1,460 ops/sec on the Wikipedia fixtures and >20 k ops/sec on micro HOCR payloads.
 - **PHP and WASM stay in the 35–70 MB/s band**, which is plenty for Composer queues or edge runtimes as long as the extension/module is built ahead of time.
 - **Rust CLI results now mirror the bindings**, since `task bench:bindings` runs the harness with `cargo run --release` by default—profile there, then push optimizations down into each FFI layer.
 
@@ -185,20 +198,20 @@ Derived directly from `tools/runtime-bench/results/latest.json` (Apple M4, share
 
 Measured on Apple M4 using the fixture-driven runtime harness in `tools/runtime-bench` (`task bench:bindings`). Every binding consumes the exact same HTML fixtures and hOCR samples from `test_documents/`:
 
-| Document            | Size     | Ruby ops/sec | PHP ops/sec | Python ops/sec | Node ops/sec | WASM ops/sec | Rust ops/sec |
-| ------------------- | -------- | ------------ | ----------- | -------------- | ------------ | ------------ | ------------ |
-| Lists (Timeline)    | 129 KB   | 1,349        | 533         | 1,405          | 1,308        | 882          | **1,700**    |
-| Tables (Countries)  | 360 KB   | 326          | 118         | 352            | 331          | 242          | **416**      |
-| Medium (Python)     | 657 KB   | 157          | 59          | 158            | 150          | 121          | **190**      |
-| Large (Rust)        | 567 KB   | 174          | 65          | 183            | 163          | 124          | **220**      |
-| Small (Intro)       | 463 KB   | 214          | 83          | 223            | 208          | 163          | **258**      |
-| HOCR German PDF     | 44 KB    | 2,936        | 1,007       | **2,991**      | 2,944        | 1,637        | 2,760        |
-| HOCR Invoice        | 4 KB     | 25,740       | 8,781       | 23,500         | 27,326       | 7,775        | **31,345**   |
-| HOCR Embedded Tables| 37 KB    | 3,328        | 1,194       | 3,464          | **3,475**    | 1,667        | 3,080        |
+| Document            | Size     | Ruby ops/sec | PHP ops/sec | Python ops/sec | Node ops/sec | WASM ops/sec | Elixir ops/sec | Rust ops/sec |
+| ------------------- | -------- | ------------ | ----------- | -------------- | ------------ | ------------ | -------------- | ------------ |
+| Lists (Timeline)    | 129 KB   | 1,349        | 533         | 1,405          | 1,308        | 882          | 1,463          | **1,700**    |
+| Tables (Countries)  | 360 KB   | 326          | 118         | 352            | 331          | 242          | 357            | **416**      |
+| Medium (Python)     | 657 KB   | 157          | 59          | 158            | 150          | 121          | 171            | **190**      |
+| Large (Rust)        | 567 KB   | 174          | 65          | 183            | 163          | 124          | 174            | **220**      |
+| Small (Intro)       | 463 KB   | 214          | 83          | 223            | 208          | 163          | 247            | **258**      |
+| HOCR German PDF     | 44 KB    | 2,936        | 1,007       | **2,991**      | 2,944        | 1,637        | 3,113          | 2,760        |
+| HOCR Invoice        | 4 KB     | 25,740       | 8,781       | 23,500         | 27,326       | 7,775        | 20,424         | **31,345**   |
+| HOCR Embedded Tables| 37 KB    | 3,328        | 1,194       | 3,464          | **3,475**    | 1,667        | 3,366          | 3,080        |
 
 The harness shells out to each runtime’s lightweight benchmark driver (`packages/*/bin/benchmark.*`, `crates/*/bin/benchmark.ts`), feeds fixtures defined in `tools/runtime-bench/fixtures/*.toml`, and writes machine-readable JSON reports (`tools/runtime-bench/results/latest.json`) for regression tracking. Add new languages or scenarios by extending those fixture files and drivers.
 
-Use `task bench:bindings` to regenerate throughput numbers across all bindings or `task bench:bindings:profile` to capture CPU/memory samples while the benchmarks run. To focus on specific languages or fixtures, pass `--language` / `--fixture` directly to `cargo run --manifest-path tools/runtime-bench/Cargo.toml -- …`.
+Use `task bench:bindings` to regenerate throughput numbers across all bindings or `task bench:bindings:profile` to capture CPU/memory samples while the benchmarks run. To focus on specific languages or fixtures (for example, `task bench:bindings -- --language elixir`), pass `--language` / `--fixture` directly to `cargo run --manifest-path tools/runtime-bench/Cargo.toml -- …`.
 
 Need a call-stack view of the Rust core? Run `task flamegraph:rust` (or call the harness with `--language rust --flamegraph path.svg`) to profile a fixture and dump a ready-to-inspect flamegraph in `tools/runtime-bench/results/`.
 

package/dist-web/html_to_markdown_wasm.d.ts

@@ -1,5 +1,9 @@
 /* tslint:disable */
 /* eslint-disable */
+export function createConversionOptionsHandle(options: any): WasmConversionOptionsHandle;
+export function convertWithInlineImages(html: string, options: any, image_config?: WasmInlineImageConfig | null): WasmHtmlExtraction;
+export function convertBytesWithOptionsHandle(html: Uint8Array, handle: WasmConversionOptionsHandle): string;
+export function convertWithOptionsHandle(html: string, handle: WasmConversionOptionsHandle): string;
 export function convertBytes(html: Uint8Array, options: any): string;
 /**
  * Convert HTML to Markdown
@@ -20,15 +24,11 @@ export function convertBytes(html: Uint8Array, options: any): string;
  * ```
  */
 export function convert(html: string, options: any): string;
-export function convertWithOptionsHandle(html: string, handle: WasmConversionOptionsHandle): string;
+export function convertBytesWithInlineImages(html: Uint8Array, options: any, image_config?: WasmInlineImageConfig | null): WasmHtmlExtraction;
 /**
  * Initialize panic hook for better error messages in the browser
  */
 export function init(): void;
-export function convertBytesWithInlineImages(html: Uint8Array, options: any, image_config?: WasmInlineImageConfig | null): WasmHtmlExtraction;
-export function createConversionOptionsHandle(options: any): WasmConversionOptionsHandle;
-export function convertBytesWithOptionsHandle(html: Uint8Array, handle: WasmConversionOptionsHandle): string;
-export function convertWithInlineImages(html: string, options: any, image_config?: WasmInlineImageConfig | null): WasmHtmlExtraction;
 export class WasmConversionOptionsHandle {
   free(): void;
   [Symbol.dispose](): void;