html-to-markdown-wasm 2.8.0 → 2.8.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (16) hide show
  1. package/dist/README.md +25 -12
  2. package/dist/html_to_markdown_wasm.d.ts +5 -5
  3. package/dist/html_to_markdown_wasm_bg.js +108 -108
  4. package/dist/html_to_markdown_wasm_bg.wasm +0 -0
  5. package/dist/package.json +1 -1
  6. package/dist-node/README.md +25 -12
  7. package/dist-node/html_to_markdown_wasm.d.ts +5 -5
  8. package/dist-node/html_to_markdown_wasm.js +108 -108
  9. package/dist-node/html_to_markdown_wasm_bg.wasm +0 -0
  10. package/dist-node/package.json +1 -1
  11. package/dist-web/README.md +25 -12
  12. package/dist-web/html_to_markdown_wasm.d.ts +5 -5
  13. package/dist-web/html_to_markdown_wasm.js +108 -108
  14. package/dist-web/html_to_markdown_wasm_bg.wasm +0 -0
  15. package/dist-web/package.json +1 -1
  16. package/package.json +1 -1
package/dist/README.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # html-to-markdown
2
2
 
3
- 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.
3
+ 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.
4
4
 
5
5
  [![Crates.io](https://img.shields.io/crates/v/html-to-markdown.svg)](https://crates.io/crates/html-to-markdown)
6
6
  [![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
8
8
  [![PyPI](https://badge.fury.io/py/html-to-markdown.svg)](https://pypi.org/project/html-to-markdown/)
9
9
  [![Packagist](https://img.shields.io/packagist/v/goldziher/html-to-markdown.svg)](https://packagist.org/packages/goldziher/html-to-markdown)
10
10
  [![RubyGems](https://badge.fury.io/rb/html-to-markdown.svg)](https://rubygems.org/gems/html-to-markdown)
11
+ [![Hex.pm](https://img.shields.io/hexpm/v/html_to_markdown.svg)](https://hex.pm/packages/html_to_markdown)
11
12
  [![NuGet](https://img.shields.io/nuget/v/HtmlToMarkdown.svg)](https://www.nuget.org/packages/HtmlToMarkdown/)
12
13
  [![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)
13
14
  [![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
43
44
  - PHP wrapper package – [PHP README](https://github.com/Goldziher/html-to-markdown/blob/main/packages/php/README.md)
44
45
  - PHP extension (PIE) – [Extension README](https://github.com/Goldziher/html-to-markdown/blob/main/packages/php-ext/README.md)
45
46
  - **Ruby guide** – [Ruby README](https://github.com/Goldziher/html-to-markdown/blob/main/packages/ruby/README.md)
47
+ - **Elixir guide** – [Elixir README](https://github.com/Goldziher/html-to-markdown/blob/main/packages/elixir/README.md)
46
48
  - **Rust guide** – [Rust README](https://github.com/Goldziher/html-to-markdown/blob/main/crates/html-to-markdown/README.md)
47
49
  - **Contributing** – [CONTRIBUTING.md](https://github.com/Goldziher/html-to-markdown/blob/main/CONTRIBUTING.md) ⭐ Start here!
48
50
  - **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
57
59
  | **Python** (bindings + CLI) | `pip install html-to-markdown` |
58
60
  | **PHP** (extension + helpers) | `pie install goldziher/html-to-markdown`<br>`composer require html-to-markdown/extension` |
59
61
  | **Ruby** gem | `bundle add html-to-markdown` or `gem install html-to-markdown` |
62
+ | **Elixir** (Rustler NIF) | `{:html_to_markdown, "~> 2.8"}` |
60
63
  | **Rust** crate | `cargo add html-to-markdown-rs` |
61
64
  | Rust CLI | `cargo install html-to-markdown-cli` |
62
65
  | Homebrew CLI | `brew tap goldziher/tap`<br>`brew install html-to-markdown` |
@@ -126,6 +129,15 @@ markdown, inline_images, warnings = convert_with_inline_images(
126
129
  )
127
130
  ```
128
131
 
132
+ ### Elixir
133
+
134
+ ```elixir
135
+ {:ok, markdown} = HtmlToMarkdown.convert("<h1>Hello</h1>")
136
+
137
+ # Keyword options are supported (internally mapped to the Rust ConversionOptions struct)
138
+ HtmlToMarkdown.convert!("<p>Wrap me</p>", wrap: true, wrap_width: 32, preprocessing: %{enabled: true})
139
+ ```
140
+
129
141
  ### Rust
130
142
 
131
143
  ```rust
@@ -178,6 +190,7 @@ Derived directly from `tools/runtime-bench/results/latest.json` (Apple M4, share
178
190
  - **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.
179
191
  - **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.
180
192
  - **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.
193
+ - **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.
181
194
  - **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.
182
195
  - **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.
183
196
 
@@ -185,20 +198,20 @@ Derived directly from `tools/runtime-bench/results/latest.json` (Apple M4, share
185
198
 
186
199
  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/`:
187
200
 
188
- | Document | Size | Ruby ops/sec | PHP ops/sec | Python ops/sec | Node ops/sec | WASM ops/sec | Rust ops/sec |
189
- | ------------------- | -------- | ------------ | ----------- | -------------- | ------------ | ------------ | ------------ |
190
- | Lists (Timeline) | 129 KB | 1,349 | 533 | 1,405 | 1,308 | 882 | **1,700** |
191
- | Tables (Countries) | 360 KB | 326 | 118 | 352 | 331 | 242 | **416** |
192
- | Medium (Python) | 657 KB | 157 | 59 | 158 | 150 | 121 | **190** |
193
- | Large (Rust) | 567 KB | 174 | 65 | 183 | 163 | 124 | **220** |
194
- | Small (Intro) | 463 KB | 214 | 83 | 223 | 208 | 163 | **258** |
195
- | HOCR German PDF | 44 KB | 2,936 | 1,007 | **2,991** | 2,944 | 1,637 | 2,760 |
196
- | HOCR Invoice | 4 KB | 25,740 | 8,781 | 23,500 | 27,326 | 7,775 | **31,345** |
197
- | HOCR Embedded Tables| 37 KB | 3,328 | 1,194 | 3,464 | **3,475** | 1,667 | 3,080 |
201
+ | Document | Size | Ruby ops/sec | PHP ops/sec | Python ops/sec | Node ops/sec | WASM ops/sec | Elixir ops/sec | Rust ops/sec |
202
+ | ------------------- | -------- | ------------ | ----------- | -------------- | ------------ | ------------ | -------------- | ------------ |
203
+ | Lists (Timeline) | 129 KB | 1,349 | 533 | 1,405 | 1,308 | 882 | 1,463 | **1,700** |
204
+ | Tables (Countries) | 360 KB | 326 | 118 | 352 | 331 | 242 | 357 | **416** |
205
+ | Medium (Python) | 657 KB | 157 | 59 | 158 | 150 | 121 | 171 | **190** |
206
+ | Large (Rust) | 567 KB | 174 | 65 | 183 | 163 | 124 | 174 | **220** |
207
+ | Small (Intro) | 463 KB | 214 | 83 | 223 | 208 | 163 | 247 | **258** |
208
+ | HOCR German PDF | 44 KB | 2,936 | 1,007 | **2,991** | 2,944 | 1,637 | 3,113 | 2,760 |
209
+ | HOCR Invoice | 4 KB | 25,740 | 8,781 | 23,500 | 27,326 | 7,775 | 20,424 | **31,345** |
210
+ | HOCR Embedded Tables| 37 KB | 3,328 | 1,194 | 3,464 | **3,475** | 1,667 | 3,366 | 3,080 |
198
211
 
199
212
  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.
200
213
 
201
- 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 -- …`.
214
+ 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 -- …`.
202
215
 
203
216
  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/`.
204
217
 
package/dist/html_to_markdown_wasm.d.ts CHANGED
@@ -1,5 +1,9 @@
1
1
  /* tslint:disable */
2
2
  /* eslint-disable */
3
+ export function createConversionOptionsHandle(options: any): WasmConversionOptionsHandle;
4
+ export function convertWithInlineImages(html: string, options: any, image_config?: WasmInlineImageConfig | null): WasmHtmlExtraction;
5
+ export function convertBytesWithOptionsHandle(html: Uint8Array, handle: WasmConversionOptionsHandle): string;
6
+ export function convertWithOptionsHandle(html: string, handle: WasmConversionOptionsHandle): string;
3
7
  export function convertBytes(html: Uint8Array, options: any): string;
4
8
  /**
5
9
  * Convert HTML to Markdown
@@ -20,15 +24,11 @@ export function convertBytes(html: Uint8Array, options: any): string;
20
24
  * ```
21
25
  */
22
26
  export function convert(html: string, options: any): string;
23
- export function convertWithOptionsHandle(html: string, handle: WasmConversionOptionsHandle): string;
27
+ export function convertBytesWithInlineImages(html: Uint8Array, options: any, image_config?: WasmInlineImageConfig | null): WasmHtmlExtraction;
24
28
  /**
25
29
  * Initialize panic hook for better error messages in the browser
26
30
  */
27
31
  export function init(): void;
28
- export function convertBytesWithInlineImages(html: Uint8Array, options: any, image_config?: WasmInlineImageConfig | null): WasmHtmlExtraction;
29
- export function createConversionOptionsHandle(options: any): WasmConversionOptionsHandle;
30
- export function convertBytesWithOptionsHandle(html: Uint8Array, handle: WasmConversionOptionsHandle): string;
31
- export function convertWithInlineImages(html: string, options: any, image_config?: WasmInlineImageConfig | null): WasmHtmlExtraction;
32
32
  export class WasmConversionOptionsHandle {
33
33
  free(): void;
34
34
  [Symbol.dispose](): void;
package/dist/html_to_markdown_wasm_bg.js CHANGED
@@ -232,88 +232,90 @@ function getArrayJsValueFromWasm0(ptr, len) {
232
232
  return result;
233
233
  }
234
234
  /**
235
- * @param {Uint8Array} html
236
235
  * @param {any} options
237
- * @returns {string}
236
+ * @returns {WasmConversionOptionsHandle}
238
237
  */
239
- export function convertBytes(html, options) {
240
- let deferred2_0;
241
- let deferred2_1;
238
+ export function createConversionOptionsHandle(options) {
242
239
  try {
243
240
  const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
244
- wasm.convertBytes(retptr, addHeapObject(html), addHeapObject(options));
241
+ wasm.createConversionOptionsHandle(retptr, addHeapObject(options));
245
242
  var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
246
243
  var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
247
244
  var r2 = getDataViewMemory0().getInt32(retptr + 4 * 2, true);
248
- var r3 = getDataViewMemory0().getInt32(retptr + 4 * 3, true);
249
- var ptr1 = r0;
250
- var len1 = r1;
251
- if (r3) {
252
- ptr1 = 0; len1 = 0;
253
- throw takeObject(r2);
245
+ if (r2) {
246
+ throw takeObject(r1);
254
247
  }
255
- deferred2_0 = ptr1;
256
- deferred2_1 = len1;
257
- return getStringFromWasm0(ptr1, len1);
248
+ return WasmConversionOptionsHandle.__wrap(r0);
258
249
  } finally {
259
250
  wasm.__wbindgen_add_to_stack_pointer(16);
260
- wasm.__wbindgen_export4(deferred2_0, deferred2_1, 1);
261
251
  }
262
252
  }
263
253
 
254
+ function _assertClass(instance, klass) {
255
+ if (!(instance instanceof klass)) {
256
+ throw new Error(`expected instance of ${klass.name}`);
257
+ }
258
+ }
264
259
  /**
265
- * Convert HTML to Markdown
266
- *
267
- * # Arguments
268
- *
269
- * * `html` - The HTML string to convert
270
- * * `options` - Optional conversion options (as a JavaScript object)
271
- *
272
- * # Example
273
- *
274
- * ```javascript
275
- * import { convert } from 'html-to-markdown-wasm';
276
- *
277
- * const html = '<h1>Hello World</h1>';
278
- * const markdown = convert(html);
279
- * console.log(markdown); // # Hello World
280
- * ```
281
260
  * @param {string} html
282
261
  * @param {any} options
283
- * @returns {string}
262
+ * @param {WasmInlineImageConfig | null} [image_config]
263
+ * @returns {WasmHtmlExtraction}
284
264
  */
285
- export function convert(html, options) {
286
- let deferred3_0;
287
- let deferred3_1;
265
+ export function convertWithInlineImages(html, options, image_config) {
288
266
  try {
289
267
  const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
290
268
  const ptr0 = passStringToWasm0(html, wasm.__wbindgen_export, wasm.__wbindgen_export2);
291
269
  const len0 = WASM_VECTOR_LEN;
292
- wasm.convert(retptr, ptr0, len0, addHeapObject(options));
270
+ let ptr1 = 0;
271
+ if (!isLikeNone(image_config)) {
272
+ _assertClass(image_config, WasmInlineImageConfig);
273
+ ptr1 = image_config.__destroy_into_raw();
274
+ }
275
+ wasm.convertWithInlineImages(retptr, ptr0, len0, addHeapObject(options), ptr1);
276
+ var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
277
+ var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
278
+ var r2 = getDataViewMemory0().getInt32(retptr + 4 * 2, true);
279
+ if (r2) {
280
+ throw takeObject(r1);
281
+ }
282
+ return WasmHtmlExtraction.__wrap(r0);
283
+ } finally {
284
+ wasm.__wbindgen_add_to_stack_pointer(16);
285
+ }
286
+ }
287
+
288
+ /**
289
+ * @param {Uint8Array} html
290
+ * @param {WasmConversionOptionsHandle} handle
291
+ * @returns {string}
292
+ */
293
+ export function convertBytesWithOptionsHandle(html, handle) {
294
+ let deferred2_0;
295
+ let deferred2_1;
296
+ try {
297
+ const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
298
+ _assertClass(handle, WasmConversionOptionsHandle);
299
+ wasm.convertBytesWithOptionsHandle(retptr, addHeapObject(html), handle.__wbg_ptr);
293
300
  var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
294
301
  var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
295
302
  var r2 = getDataViewMemory0().getInt32(retptr + 4 * 2, true);
296
303
  var r3 = getDataViewMemory0().getInt32(retptr + 4 * 3, true);
297
- var ptr2 = r0;
298
- var len2 = r1;
304
+ var ptr1 = r0;
305
+ var len1 = r1;
299
306
  if (r3) {
300
- ptr2 = 0; len2 = 0;
307
+ ptr1 = 0; len1 = 0;
301
308
  throw takeObject(r2);
302
309
  }
303
- deferred3_0 = ptr2;
304
- deferred3_1 = len2;
305
- return getStringFromWasm0(ptr2, len2);
310
+ deferred2_0 = ptr1;
311
+ deferred2_1 = len1;
312
+ return getStringFromWasm0(ptr1, len1);
306
313
  } finally {
307
314
  wasm.__wbindgen_add_to_stack_pointer(16);
308
- wasm.__wbindgen_export4(deferred3_0, deferred3_1, 1);
315
+ wasm.__wbindgen_export4(deferred2_0, deferred2_1, 1);
309
316
  }
310
317
  }
311
318
 
312
- function _assertClass(instance, klass) {
313
- if (!(instance instanceof klass)) {
314
- throw new Error(`expected instance of ${klass.name}`);
315
- }
316
- }
317
319
  /**
318
320
  * @param {string} html
319
321
  * @param {WasmConversionOptionsHandle} handle
@@ -347,108 +349,99 @@ export function convertWithOptionsHandle(html, handle) {
347
349
  }
348
350
  }
349
351
 
350
- /**
351
- * Initialize panic hook for better error messages in the browser
352
- */
353
- export function init() {
354
- wasm.init();
355
- }
356
-
357
352
  /**
358
353
  * @param {Uint8Array} html
359
354
  * @param {any} options
360
- * @param {WasmInlineImageConfig | null} [image_config]
361
- * @returns {WasmHtmlExtraction}
355
+ * @returns {string}
362
356
  */
363
- export function convertBytesWithInlineImages(html, options, image_config) {
357
+ export function convertBytes(html, options) {
358
+ let deferred2_0;
359
+ let deferred2_1;
364
360
  try {
365
361
  const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
366
- let ptr0 = 0;
367
- if (!isLikeNone(image_config)) {
368
- _assertClass(image_config, WasmInlineImageConfig);
369
- ptr0 = image_config.__destroy_into_raw();
370
- }
371
- wasm.convertBytesWithInlineImages(retptr, addHeapObject(html), addHeapObject(options), ptr0);
362
+ wasm.convertBytes(retptr, addHeapObject(html), addHeapObject(options));
372
363
  var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
373
364
  var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
374
365
  var r2 = getDataViewMemory0().getInt32(retptr + 4 * 2, true);
375
- if (r2) {
376
- throw takeObject(r1);
366
+ var r3 = getDataViewMemory0().getInt32(retptr + 4 * 3, true);
367
+ var ptr1 = r0;
368
+ var len1 = r1;
369
+ if (r3) {
370
+ ptr1 = 0; len1 = 0;
371
+ throw takeObject(r2);
377
372
  }
378
- return WasmHtmlExtraction.__wrap(r0);
373
+ deferred2_0 = ptr1;
374
+ deferred2_1 = len1;
375
+ return getStringFromWasm0(ptr1, len1);
379
376
  } finally {
380
377
  wasm.__wbindgen_add_to_stack_pointer(16);
378
+ wasm.__wbindgen_export4(deferred2_0, deferred2_1, 1);
381
379
  }
382
380
  }
383
381
 
384
382
  /**
383
+ * Convert HTML to Markdown
384
+ *
385
+ * # Arguments
386
+ *
387
+ * * `html` - The HTML string to convert
388
+ * * `options` - Optional conversion options (as a JavaScript object)
389
+ *
390
+ * # Example
391
+ *
392
+ * ```javascript
393
+ * import { convert } from 'html-to-markdown-wasm';
394
+ *
395
+ * const html = '<h1>Hello World</h1>';
396
+ * const markdown = convert(html);
397
+ * console.log(markdown); // # Hello World
398
+ * ```
399
+ * @param {string} html
385
400
  * @param {any} options
386
- * @returns {WasmConversionOptionsHandle}
387
- */
388
- export function createConversionOptionsHandle(options) {
389
- try {
390
- const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
391
- wasm.createConversionOptionsHandle(retptr, addHeapObject(options));
392
- var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
393
- var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
394
- var r2 = getDataViewMemory0().getInt32(retptr + 4 * 2, true);
395
- if (r2) {
396
- throw takeObject(r1);
397
- }
398
- return WasmConversionOptionsHandle.__wrap(r0);
399
- } finally {
400
- wasm.__wbindgen_add_to_stack_pointer(16);
401
- }
402
- }
403
-
404
- /**
405
- * @param {Uint8Array} html
406
- * @param {WasmConversionOptionsHandle} handle
407
401
  * @returns {string}
408
402
  */
409
- export function convertBytesWithOptionsHandle(html, handle) {
410
- let deferred2_0;
411
- let deferred2_1;
403
+ export function convert(html, options) {
404
+ let deferred3_0;
405
+ let deferred3_1;
412
406
  try {
413
407
  const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
414
- _assertClass(handle, WasmConversionOptionsHandle);
415
- wasm.convertBytesWithOptionsHandle(retptr, addHeapObject(html), handle.__wbg_ptr);
408
+ const ptr0 = passStringToWasm0(html, wasm.__wbindgen_export, wasm.__wbindgen_export2);
409
+ const len0 = WASM_VECTOR_LEN;
410
+ wasm.convert(retptr, ptr0, len0, addHeapObject(options));
416
411
  var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
417
412
  var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
418
413
  var r2 = getDataViewMemory0().getInt32(retptr + 4 * 2, true);
419
414
  var r3 = getDataViewMemory0().getInt32(retptr + 4 * 3, true);
420
- var ptr1 = r0;
421
- var len1 = r1;
415
+ var ptr2 = r0;
416
+ var len2 = r1;
422
417
  if (r3) {
423
- ptr1 = 0; len1 = 0;
418
+ ptr2 = 0; len2 = 0;
424
419
  throw takeObject(r2);
425
420
  }
426
- deferred2_0 = ptr1;
427
- deferred2_1 = len1;
428
- return getStringFromWasm0(ptr1, len1);
421
+ deferred3_0 = ptr2;
422
+ deferred3_1 = len2;
423
+ return getStringFromWasm0(ptr2, len2);
429
424
  } finally {
430
425
  wasm.__wbindgen_add_to_stack_pointer(16);
431
- wasm.__wbindgen_export4(deferred2_0, deferred2_1, 1);
426
+ wasm.__wbindgen_export4(deferred3_0, deferred3_1, 1);
432
427
  }
433
428
  }
434
429
 
435
430
  /**
436
- * @param {string} html
431
+ * @param {Uint8Array} html
437
432
  * @param {any} options
438
433
  * @param {WasmInlineImageConfig | null} [image_config]
439
434
  * @returns {WasmHtmlExtraction}
440
435
  */
441
- export function convertWithInlineImages(html, options, image_config) {
436
+ export function convertBytesWithInlineImages(html, options, image_config) {
442
437
  try {
443
438
  const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
444
- const ptr0 = passStringToWasm0(html, wasm.__wbindgen_export, wasm.__wbindgen_export2);
445
- const len0 = WASM_VECTOR_LEN;
446
- let ptr1 = 0;
439
+ let ptr0 = 0;
447
440
  if (!isLikeNone(image_config)) {
448
441
  _assertClass(image_config, WasmInlineImageConfig);
449
- ptr1 = image_config.__destroy_into_raw();
442
+ ptr0 = image_config.__destroy_into_raw();
450
443
  }
451
- wasm.convertWithInlineImages(retptr, ptr0, len0, addHeapObject(options), ptr1);
444
+ wasm.convertBytesWithInlineImages(retptr, addHeapObject(html), addHeapObject(options), ptr0);
452
445
  var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
453
446
  var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
454
447
  var r2 = getDataViewMemory0().getInt32(retptr + 4 * 2, true);
@@ -461,6 +454,13 @@ export function convertWithInlineImages(html, options, image_config) {
461
454
  }
462
455
  }
463
456
 
457
+ /**
458
+ * Initialize panic hook for better error messages in the browser
459
+ */
460
+ export function init() {
461
+ wasm.init();
462
+ }
463
+
464
464
  const WasmConversionOptionsHandleFinalization = (typeof FinalizationRegistry === 'undefined')
465
465
  ? { register: () => {}, unregister: () => {} }
466
466
  : new FinalizationRegistry(ptr => wasm.__wbg_wasmconversionoptionshandle_free(ptr >>> 0, 1));
package/dist/html_to_markdown_wasm_bg.wasm CHANGED
Binary file
package/dist/package.json CHANGED
@@ -4,7 +4,7 @@
4
4
  "collaborators": [
5
5
  "Na'aman Hirschfeld <nhirschfeld@gmail.com>"
6
6
  ],
7
- "version": "2.8.0",
7
+ "version": "2.8.2",
8
8
  "license": "MIT",
9
9
  "repository": {
10
10
  "type": "git",
package/dist-node/README.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # html-to-markdown
2
2
 
3
- 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.
3
+ 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.
4
4
 
5
5
  [![Crates.io](https://img.shields.io/crates/v/html-to-markdown.svg)](https://crates.io/crates/html-to-markdown)
6
6
  [![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
8
8
  [![PyPI](https://badge.fury.io/py/html-to-markdown.svg)](https://pypi.org/project/html-to-markdown/)
9
9
  [![Packagist](https://img.shields.io/packagist/v/goldziher/html-to-markdown.svg)](https://packagist.org/packages/goldziher/html-to-markdown)
10
10
  [![RubyGems](https://badge.fury.io/rb/html-to-markdown.svg)](https://rubygems.org/gems/html-to-markdown)
11
+ [![Hex.pm](https://img.shields.io/hexpm/v/html_to_markdown.svg)](https://hex.pm/packages/html_to_markdown)
11
12
  [![NuGet](https://img.shields.io/nuget/v/HtmlToMarkdown.svg)](https://www.nuget.org/packages/HtmlToMarkdown/)
12
13
  [![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)
13
14
  [![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
43
44
  - PHP wrapper package – [PHP README](https://github.com/Goldziher/html-to-markdown/blob/main/packages/php/README.md)
44
45
  - PHP extension (PIE) – [Extension README](https://github.com/Goldziher/html-to-markdown/blob/main/packages/php-ext/README.md)
45
46
  - **Ruby guide** – [Ruby README](https://github.com/Goldziher/html-to-markdown/blob/main/packages/ruby/README.md)
47
+ - **Elixir guide** – [Elixir README](https://github.com/Goldziher/html-to-markdown/blob/main/packages/elixir/README.md)
46
48
  - **Rust guide** – [Rust README](https://github.com/Goldziher/html-to-markdown/blob/main/crates/html-to-markdown/README.md)
47
49
  - **Contributing** – [CONTRIBUTING.md](https://github.com/Goldziher/html-to-markdown/blob/main/CONTRIBUTING.md) ⭐ Start here!
48
50
  - **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
57
59
  | **Python** (bindings + CLI) | `pip install html-to-markdown` |
58
60
  | **PHP** (extension + helpers) | `pie install goldziher/html-to-markdown`<br>`composer require html-to-markdown/extension` |
59
61
  | **Ruby** gem | `bundle add html-to-markdown` or `gem install html-to-markdown` |
62
+ | **Elixir** (Rustler NIF) | `{:html_to_markdown, "~> 2.8"}` |
60
63
  | **Rust** crate | `cargo add html-to-markdown-rs` |
61
64
  | Rust CLI | `cargo install html-to-markdown-cli` |
62
65
  | Homebrew CLI | `brew tap goldziher/tap`<br>`brew install html-to-markdown` |
@@ -126,6 +129,15 @@ markdown, inline_images, warnings = convert_with_inline_images(
126
129
  )
127
130
  ```
128
131
 
132
+ ### Elixir
133
+
134
+ ```elixir
135
+ {:ok, markdown} = HtmlToMarkdown.convert("<h1>Hello</h1>")
136
+
137
+ # Keyword options are supported (internally mapped to the Rust ConversionOptions struct)
138
+ HtmlToMarkdown.convert!("<p>Wrap me</p>", wrap: true, wrap_width: 32, preprocessing: %{enabled: true})
139
+ ```
140
+
129
141
  ### Rust
130
142
 
131
143
  ```rust
@@ -178,6 +190,7 @@ Derived directly from `tools/runtime-bench/results/latest.json` (Apple M4, share
178
190
  - **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.
179
191
  - **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.
180
192
  - **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.
193
+ - **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.
181
194
  - **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.
182
195
  - **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.
183
196
 
@@ -185,20 +198,20 @@ Derived directly from `tools/runtime-bench/results/latest.json` (Apple M4, share
185
198
 
186
199
  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/`:
187
200
 
188
- | Document | Size | Ruby ops/sec | PHP ops/sec | Python ops/sec | Node ops/sec | WASM ops/sec | Rust ops/sec |
189
- | ------------------- | -------- | ------------ | ----------- | -------------- | ------------ | ------------ | ------------ |
190
- | Lists (Timeline) | 129 KB | 1,349 | 533 | 1,405 | 1,308 | 882 | **1,700** |
191
- | Tables (Countries) | 360 KB | 326 | 118 | 352 | 331 | 242 | **416** |
192
- | Medium (Python) | 657 KB | 157 | 59 | 158 | 150 | 121 | **190** |
193
- | Large (Rust) | 567 KB | 174 | 65 | 183 | 163 | 124 | **220** |
194
- | Small (Intro) | 463 KB | 214 | 83 | 223 | 208 | 163 | **258** |
195
- | HOCR German PDF | 44 KB | 2,936 | 1,007 | **2,991** | 2,944 | 1,637 | 2,760 |
196
- | HOCR Invoice | 4 KB | 25,740 | 8,781 | 23,500 | 27,326 | 7,775 | **31,345** |
197
- | HOCR Embedded Tables| 37 KB | 3,328 | 1,194 | 3,464 | **3,475** | 1,667 | 3,080 |
201
+ | Document | Size | Ruby ops/sec | PHP ops/sec | Python ops/sec | Node ops/sec | WASM ops/sec | Elixir ops/sec | Rust ops/sec |
202
+ | ------------------- | -------- | ------------ | ----------- | -------------- | ------------ | ------------ | -------------- | ------------ |
203
+ | Lists (Timeline) | 129 KB | 1,349 | 533 | 1,405 | 1,308 | 882 | 1,463 | **1,700** |
204
+ | Tables (Countries) | 360 KB | 326 | 118 | 352 | 331 | 242 | 357 | **416** |
205
+ | Medium (Python) | 657 KB | 157 | 59 | 158 | 150 | 121 | 171 | **190** |
206
+ | Large (Rust) | 567 KB | 174 | 65 | 183 | 163 | 124 | 174 | **220** |
207
+ | Small (Intro) | 463 KB | 214 | 83 | 223 | 208 | 163 | 247 | **258** |
208
+ | HOCR German PDF | 44 KB | 2,936 | 1,007 | **2,991** | 2,944 | 1,637 | 3,113 | 2,760 |
209
+ | HOCR Invoice | 4 KB | 25,740 | 8,781 | 23,500 | 27,326 | 7,775 | 20,424 | **31,345** |
210
+ | HOCR Embedded Tables| 37 KB | 3,328 | 1,194 | 3,464 | **3,475** | 1,667 | 3,366 | 3,080 |
198
211
 
199
212
  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.
200
213
 
201
- 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 -- …`.
214
+ 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 -- …`.
202
215
 
203
216
  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/`.
204
217
 
package/dist-node/html_to_markdown_wasm.d.ts CHANGED
@@ -1,5 +1,9 @@
1
1
  /* tslint:disable */
2
2
  /* eslint-disable */
3
+ export function createConversionOptionsHandle(options: any): WasmConversionOptionsHandle;
4
+ export function convertWithInlineImages(html: string, options: any, image_config?: WasmInlineImageConfig | null): WasmHtmlExtraction;
5
+ export function convertBytesWithOptionsHandle(html: Uint8Array, handle: WasmConversionOptionsHandle): string;
6
+ export function convertWithOptionsHandle(html: string, handle: WasmConversionOptionsHandle): string;
3
7
  export function convertBytes(html: Uint8Array, options: any): string;
4
8
  /**
5
9
  * Convert HTML to Markdown
@@ -20,15 +24,11 @@ export function convertBytes(html: Uint8Array, options: any): string;
20
24
  * ```
21
25
  */
22
26
  export function convert(html: string, options: any): string;
23
- export function convertWithOptionsHandle(html: string, handle: WasmConversionOptionsHandle): string;
27
+ export function convertBytesWithInlineImages(html: Uint8Array, options: any, image_config?: WasmInlineImageConfig | null): WasmHtmlExtraction;
24
28
  /**
25
29
  * Initialize panic hook for better error messages in the browser
26
30
  */
27
31
  export function init(): void;
28
- export function convertBytesWithInlineImages(html: Uint8Array, options: any, image_config?: WasmInlineImageConfig | null): WasmHtmlExtraction;
29
- export function createConversionOptionsHandle(options: any): WasmConversionOptionsHandle;
30
- export function convertBytesWithOptionsHandle(html: Uint8Array, handle: WasmConversionOptionsHandle): string;
31
- export function convertWithInlineImages(html: string, options: any, image_config?: WasmInlineImageConfig | null): WasmHtmlExtraction;
32
32
  export class WasmConversionOptionsHandle {
33
33
  free(): void;
34
34
  [Symbol.dispose](): void;