@kreuzberg/html-to-markdown-wasm 3.6.10 → 3.6.12

package/README.md

@@ -2,7 +2,7 @@
 
 <div align="center" style="display: flex; flex-wrap: wrap; gap: 8px; justify-content: center; margin: 20px 0;">
   <a href="https://github.com/kreuzberg-dev/alef">
-    <img src="https://img.shields.io/badge/Bindings-alef%20%D7%90-007ec6" alt="Bindings">
+    <img src="https://img.shields.io/badge/built%20with-alef%20%D7%90-007ec6" alt="Built with alef">
   </a>
   <!-- Language Bindings -->
   <a href="https://crates.io/crates/html-to-markdown-rs">
@@ -153,14 +153,13 @@ The dispatcher is invisible to the caller. Output is byte-identical across tiers
 
 **`ConversionOptions`** – Key configuration fields:
 
-- `heading_style`: Heading format (`"underlined"` | `"atx"` | `"atx_closed"`) — default: `"underlined"`
+- `heading_style`: Heading format (`"underlined"` | `"atx"` | `"atx_closed"`) — default: `"atx"`
 - `list_indent_width`: Spaces per indent level — default: `2`
-- `bullets`: Bullet characters cycle — default: `"*+-"`
+- `bullets`: Bullet characters cycle — default: `"-*+"`
 - `wrap`: Enable text wrapping — default: `false`
 - `wrap_width`: Wrap at column — default: `80`
 - `code_language`: Default fenced code block language — default: none
-- `extract_metadata`: Enable metadata extraction into `result.metadata` — default: `false`
-- `extract_tables`: Enable structured table extraction into `result.tables` — default: `false`
+- `extract_metadata`: Enable metadata extraction into `result.metadata` — default: `true`
 - `output_format`: Output markup format (`"markdown"` | `"djot"` | `"plain"`) — default: `"markdown"`
 
 ## Djot Output Format
@@ -214,13 +213,13 @@ The metadata extraction feature enables comprehensive document analysis during c
 
 ## Part of Kreuzberg.dev
 
-- [Kreuzberg](https://github.com/kreuzberg-dev/kreuzberg) — document intelligence: text, tables, metadata from 90+ formats with optional OCR.
+- [Kreuzberg](https://github.com/kreuzberg-dev/kreuzberg) — document intelligence: text, tables, metadata from 91+ formats with optional OCR.
 - [Kreuzberg Cloud](https://github.com/kreuzberg-dev/kreuzberg-cloud) — managed extraction API with SDKs, dashboards, and observability.
 - [kreuzcrawl](https://github.com/kreuzberg-dev/kreuzcrawl) — web crawling and scraping with HTML→Markdown and headless-Chrome fallback.
+- [html-to-markdown](https://github.com/kreuzberg-dev/html-to-markdown) — fast, lossless HTML→Markdown engine.
 - [liter-llm](https://github.com/kreuzberg-dev/liter-llm) — universal LLM API client with native bindings for 14 languages and 143 providers.
 - [tree-sitter-language-pack](https://github.com/kreuzberg-dev/tree-sitter-language-pack) — tree-sitter grammars and code-intelligence primitives.
 - [alef](https://github.com/kreuzberg-dev/alef) — the polyglot binding generator that produces every per-language binding across the 5 polyglot repos.
-- [Discord](https://discord.gg/xt9WY3GnKR) — community, roadmap, announcements.
 
 ## Contributing
 
@@ -248,5 +247,4 @@ If you find this library useful, consider [sponsoring the project](https://githu
 Have questions or run into issues? We're here to help:
 
 - **GitHub Issues:** [github.com/kreuzberg-dev/html-to-markdown/issues](https://github.com/kreuzberg-dev/html-to-markdown/issues)
-- **Issues:** [github.com/kreuzberg-dev/html-to-markdown/issues](https://github.com/kreuzberg-dev/html-to-markdown/issues)
 - **Discord Community:** [discord.gg/xt9WY3GnKR](https://discord.gg/xt9WY3GnKR)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@kreuzberg/html-to-markdown-wasm",
-  "version": "3.6.10",
+  "version": "3.6.12",
   "private": false,
   "description": "High-performance HTML to Markdown converter",
   "license": "MIT",

package/pkg/bundler/README.md

@@ -2,7 +2,7 @@
 
 <div align="center" style="display: flex; flex-wrap: wrap; gap: 8px; justify-content: center; margin: 20px 0;">
   <a href="https://github.com/kreuzberg-dev/alef">
-    <img src="https://img.shields.io/badge/Bindings-alef%20%D7%90-007ec6" alt="Bindings">
+    <img src="https://img.shields.io/badge/built%20with-alef%20%D7%90-007ec6" alt="Built with alef">
   </a>
   <!-- Language Bindings -->
   <a href="https://crates.io/crates/html-to-markdown-rs">
@@ -153,14 +153,13 @@ The dispatcher is invisible to the caller. Output is byte-identical across tiers
 
 **`ConversionOptions`** – Key configuration fields:
 
-- `heading_style`: Heading format (`"underlined"` | `"atx"` | `"atx_closed"`) — default: `"underlined"`
+- `heading_style`: Heading format (`"underlined"` | `"atx"` | `"atx_closed"`) — default: `"atx"`
 - `list_indent_width`: Spaces per indent level — default: `2`
-- `bullets`: Bullet characters cycle — default: `"*+-"`
+- `bullets`: Bullet characters cycle — default: `"-*+"`
 - `wrap`: Enable text wrapping — default: `false`
 - `wrap_width`: Wrap at column — default: `80`
 - `code_language`: Default fenced code block language — default: none
-- `extract_metadata`: Enable metadata extraction into `result.metadata` — default: `false`
-- `extract_tables`: Enable structured table extraction into `result.tables` — default: `false`
+- `extract_metadata`: Enable metadata extraction into `result.metadata` — default: `true`
 - `output_format`: Output markup format (`"markdown"` | `"djot"` | `"plain"`) — default: `"markdown"`
 
 ## Djot Output Format
@@ -214,13 +213,13 @@ The metadata extraction feature enables comprehensive document analysis during c
 
 ## Part of Kreuzberg.dev
 
-- [Kreuzberg](https://github.com/kreuzberg-dev/kreuzberg) — document intelligence: text, tables, metadata from 90+ formats with optional OCR.
+- [Kreuzberg](https://github.com/kreuzberg-dev/kreuzberg) — document intelligence: text, tables, metadata from 91+ formats with optional OCR.
 - [Kreuzberg Cloud](https://github.com/kreuzberg-dev/kreuzberg-cloud) — managed extraction API with SDKs, dashboards, and observability.
 - [kreuzcrawl](https://github.com/kreuzberg-dev/kreuzcrawl) — web crawling and scraping with HTML→Markdown and headless-Chrome fallback.
+- [html-to-markdown](https://github.com/kreuzberg-dev/html-to-markdown) — fast, lossless HTML→Markdown engine.
 - [liter-llm](https://github.com/kreuzberg-dev/liter-llm) — universal LLM API client with native bindings for 14 languages and 143 providers.
 - [tree-sitter-language-pack](https://github.com/kreuzberg-dev/tree-sitter-language-pack) — tree-sitter grammars and code-intelligence primitives.
 - [alef](https://github.com/kreuzberg-dev/alef) — the polyglot binding generator that produces every per-language binding across the 5 polyglot repos.
-- [Discord](https://discord.gg/xt9WY3GnKR) — community, roadmap, announcements.
 
 ## Contributing
 
@@ -248,5 +247,4 @@ If you find this library useful, consider [sponsoring the project](https://githu
 Have questions or run into issues? We're here to help:
 
 - **GitHub Issues:** [github.com/kreuzberg-dev/html-to-markdown/issues](https://github.com/kreuzberg-dev/html-to-markdown/issues)
-- **Issues:** [github.com/kreuzberg-dev/html-to-markdown/issues](https://github.com/kreuzberg-dev/html-to-markdown/issues)
 - **Discord Community:** [discord.gg/xt9WY3GnKR](https://discord.gg/xt9WY3GnKR)

package/pkg/bundler/html_to_markdown_wasm.d.ts

@@ -608,8 +608,7 @@ export class WasmNodeContext {
     /**
      * Construct a `NodeContext` with an owned attribute map.
      *
-     * Prefer `NodeContext.with_lazy_attributes` (pub(crate)) inside the
-     * converter to avoid the eager `collect_tag_attributes` allocation.
+     * Use this when the caller already has materialized attributes.
      */
     static withOwnedAttributes(node_type: WasmNodeType, tag_name: string, attributes: any, depth: number, index_in_parent: number, parent_tag: string | null | undefined, is_inline: boolean): WasmNodeContext;
     depth: number;
@@ -869,8 +868,7 @@ export class WasmTableGrid {
  * similar — that spans a contiguous run of bytes inside `DocumentNode.content`'s text field.
  *
  * Byte offsets (`start`..`end`) are into the UTF-8 encoded text of the parent node. The range
- * follows Rust slice conventions: `start` is inclusive and `end` is exclusive, so the annotated
- * text is `text[start as usize..end as usize]`.
+ * is half-open: `start` is inclusive and `end` is exclusive.
  *
  * Multiple annotations on the same node can overlap (e.g. bold-italic text), and they are
  * stored in the order they are encountered during DOM traversal.
@@ -987,9 +985,9 @@ export enum WasmWhitespaceMode {
  * # Arguments
  *
  * * `html` — the HTML string to convert.
- * * `options` — conversion options. Rust accepts either bare
- *   `ConversionOptions`, `Some(options)`, or `None`; bindings expose the same
- *   option fields through language-native constructors or optional parameters.
+ * * `options` — conversion options. Rust accepts bare `ConversionOptions`,
+ *   `Some(options)`, or `None`. Language bindings expose the same option
+ *   fields through native constructors or optional parameters.
  *
  * # Example
  *

package/pkg/bundler/html_to_markdown_wasm_bg.js

@@ -4573,8 +4573,7 @@ export class WasmNodeContext {
     /**
      * Construct a `NodeContext` with an owned attribute map.
      *
-     * Prefer `NodeContext.with_lazy_attributes` (pub(crate)) inside the
-     * converter to avoid the eager `collect_tag_attributes` allocation.
+     * Use this when the caller already has materialized attributes.
      * @param {WasmNodeType} node_type
      * @param {string} tag_name
      * @param {any} attributes
@@ -5387,8 +5386,7 @@ if (Symbol.dispose) WasmTableGrid.prototype[Symbol.dispose] = WasmTableGrid.prot
  * similar — that spans a contiguous run of bytes inside `DocumentNode.content`'s text field.
  *
  * Byte offsets (`start`..`end`) are into the UTF-8 encoded text of the parent node. The range
- * follows Rust slice conventions: `start` is inclusive and `end` is exclusive, so the annotated
- * text is `text[start as usize..end as usize]`.
+ * is half-open: `start` is inclusive and `end` is exclusive.
  *
  * Multiple annotations on the same node can overlap (e.g. bold-italic text), and they are
  * stored in the order they are encountered during DOM traversal.
@@ -5607,9 +5605,9 @@ export const WasmWhitespaceMode = Object.freeze({
  * # Arguments
  *
  * * `html` — the HTML string to convert.
- * * `options` — conversion options. Rust accepts either bare
- *   `ConversionOptions`, `Some(options)`, or `None`; bindings expose the same
- *   option fields through language-native constructors or optional parameters.
+ * * `options` — conversion options. Rust accepts bare `ConversionOptions`,
+ *   `Some(options)`, or `None`. Language bindings expose the same option
+ *   fields through native constructors or optional parameters.
  *
  * # Example
  *

package/pkg/bundler/package.json

@@ -2,7 +2,7 @@
   "name": "html-to-markdown-wasm",
   "type": "module",
   "description": "High-performance HTML to Markdown converter",
-  "version": "3.6.10",
+  "version": "3.6.12",
   "license": "MIT",
   "repository": {
     "type": "git",

package/pkg/deno/README.md

@@ -2,7 +2,7 @@
 
 <div align="center" style="display: flex; flex-wrap: wrap; gap: 8px; justify-content: center; margin: 20px 0;">
   <a href="https://github.com/kreuzberg-dev/alef">
-    <img src="https://img.shields.io/badge/Bindings-alef%20%D7%90-007ec6" alt="Bindings">
+    <img src="https://img.shields.io/badge/built%20with-alef%20%D7%90-007ec6" alt="Built with alef">
   </a>
   <!-- Language Bindings -->
   <a href="https://crates.io/crates/html-to-markdown-rs">
@@ -153,14 +153,13 @@ The dispatcher is invisible to the caller. Output is byte-identical across tiers
 
 **`ConversionOptions`** – Key configuration fields:
 
-- `heading_style`: Heading format (`"underlined"` | `"atx"` | `"atx_closed"`) — default: `"underlined"`
+- `heading_style`: Heading format (`"underlined"` | `"atx"` | `"atx_closed"`) — default: `"atx"`
 - `list_indent_width`: Spaces per indent level — default: `2`
-- `bullets`: Bullet characters cycle — default: `"*+-"`
+- `bullets`: Bullet characters cycle — default: `"-*+"`
 - `wrap`: Enable text wrapping — default: `false`
 - `wrap_width`: Wrap at column — default: `80`
 - `code_language`: Default fenced code block language — default: none
-- `extract_metadata`: Enable metadata extraction into `result.metadata` — default: `false`
-- `extract_tables`: Enable structured table extraction into `result.tables` — default: `false`
+- `extract_metadata`: Enable metadata extraction into `result.metadata` — default: `true`
 - `output_format`: Output markup format (`"markdown"` | `"djot"` | `"plain"`) — default: `"markdown"`
 
 ## Djot Output Format
@@ -214,13 +213,13 @@ The metadata extraction feature enables comprehensive document analysis during c
 
 ## Part of Kreuzberg.dev
 
-- [Kreuzberg](https://github.com/kreuzberg-dev/kreuzberg) — document intelligence: text, tables, metadata from 90+ formats with optional OCR.
+- [Kreuzberg](https://github.com/kreuzberg-dev/kreuzberg) — document intelligence: text, tables, metadata from 91+ formats with optional OCR.
 - [Kreuzberg Cloud](https://github.com/kreuzberg-dev/kreuzberg-cloud) — managed extraction API with SDKs, dashboards, and observability.
 - [kreuzcrawl](https://github.com/kreuzberg-dev/kreuzcrawl) — web crawling and scraping with HTML→Markdown and headless-Chrome fallback.
+- [html-to-markdown](https://github.com/kreuzberg-dev/html-to-markdown) — fast, lossless HTML→Markdown engine.
 - [liter-llm](https://github.com/kreuzberg-dev/liter-llm) — universal LLM API client with native bindings for 14 languages and 143 providers.
 - [tree-sitter-language-pack](https://github.com/kreuzberg-dev/tree-sitter-language-pack) — tree-sitter grammars and code-intelligence primitives.
 - [alef](https://github.com/kreuzberg-dev/alef) — the polyglot binding generator that produces every per-language binding across the 5 polyglot repos.
-- [Discord](https://discord.gg/xt9WY3GnKR) — community, roadmap, announcements.
 
 ## Contributing
 
@@ -248,5 +247,4 @@ If you find this library useful, consider [sponsoring the project](https://githu
 Have questions or run into issues? We're here to help:
 
 - **GitHub Issues:** [github.com/kreuzberg-dev/html-to-markdown/issues](https://github.com/kreuzberg-dev/html-to-markdown/issues)
-- **Issues:** [github.com/kreuzberg-dev/html-to-markdown/issues](https://github.com/kreuzberg-dev/html-to-markdown/issues)
 - **Discord Community:** [discord.gg/xt9WY3GnKR](https://discord.gg/xt9WY3GnKR)

package/pkg/deno/html_to_markdown_wasm.d.ts

@@ -608,8 +608,7 @@ export class WasmNodeContext {
     /**
      * Construct a `NodeContext` with an owned attribute map.
      *
-     * Prefer `NodeContext.with_lazy_attributes` (pub(crate)) inside the
-     * converter to avoid the eager `collect_tag_attributes` allocation.
+     * Use this when the caller already has materialized attributes.
      */
     static withOwnedAttributes(node_type: WasmNodeType, tag_name: string, attributes: any, depth: number, index_in_parent: number, parent_tag: string | null | undefined, is_inline: boolean): WasmNodeContext;
     depth: number;
@@ -869,8 +868,7 @@ export class WasmTableGrid {
  * similar — that spans a contiguous run of bytes inside `DocumentNode.content`'s text field.
  *
  * Byte offsets (`start`..`end`) are into the UTF-8 encoded text of the parent node. The range
- * follows Rust slice conventions: `start` is inclusive and `end` is exclusive, so the annotated
- * text is `text[start as usize..end as usize]`.
+ * is half-open: `start` is inclusive and `end` is exclusive.
  *
  * Multiple annotations on the same node can overlap (e.g. bold-italic text), and they are
  * stored in the order they are encountered during DOM traversal.
@@ -987,9 +985,9 @@ export enum WasmWhitespaceMode {
  * # Arguments
  *
  * * `html` — the HTML string to convert.
- * * `options` — conversion options. Rust accepts either bare
- *   `ConversionOptions`, `Some(options)`, or `None`; bindings expose the same
- *   option fields through language-native constructors or optional parameters.
+ * * `options` — conversion options. Rust accepts bare `ConversionOptions`,
+ *   `Some(options)`, or `None`. Language bindings expose the same option
+ *   fields through native constructors or optional parameters.
  *
  * # Example
  *

package/pkg/deno/html_to_markdown_wasm.js

@@ -4575,8 +4575,7 @@ export class WasmNodeContext {
     /**
      * Construct a `NodeContext` with an owned attribute map.
      *
-     * Prefer `NodeContext.with_lazy_attributes` (pub(crate)) inside the
-     * converter to avoid the eager `collect_tag_attributes` allocation.
+     * Use this when the caller already has materialized attributes.
      * @param {WasmNodeType} node_type
      * @param {string} tag_name
      * @param {any} attributes
@@ -5389,8 +5388,7 @@ if (Symbol.dispose) WasmTableGrid.prototype[Symbol.dispose] = WasmTableGrid.prot
  * similar — that spans a contiguous run of bytes inside `DocumentNode.content`'s text field.
  *
  * Byte offsets (`start`..`end`) are into the UTF-8 encoded text of the parent node. The range
- * follows Rust slice conventions: `start` is inclusive and `end` is exclusive, so the annotated
- * text is `text[start as usize..end as usize]`.
+ * is half-open: `start` is inclusive and `end` is exclusive.
  *
  * Multiple annotations on the same node can overlap (e.g. bold-italic text), and they are
  * stored in the order they are encountered during DOM traversal.
@@ -5609,9 +5607,9 @@ export const WasmWhitespaceMode = Object.freeze({
  * # Arguments
  *
  * * `html` — the HTML string to convert.
- * * `options` — conversion options. Rust accepts either bare
- *   `ConversionOptions`, `Some(options)`, or `None`; bindings expose the same
- *   option fields through language-native constructors or optional parameters.
+ * * `options` — conversion options. Rust accepts bare `ConversionOptions`,
+ *   `Some(options)`, or `None`. Language bindings expose the same option
+ *   fields through native constructors or optional parameters.
  *
  * # Example
  *

package/pkg/nodejs/README.md

@@ -2,7 +2,7 @@
 
 <div align="center" style="display: flex; flex-wrap: wrap; gap: 8px; justify-content: center; margin: 20px 0;">
   <a href="https://github.com/kreuzberg-dev/alef">
-    <img src="https://img.shields.io/badge/Bindings-alef%20%D7%90-007ec6" alt="Bindings">
+    <img src="https://img.shields.io/badge/built%20with-alef%20%D7%90-007ec6" alt="Built with alef">
   </a>
   <!-- Language Bindings -->
   <a href="https://crates.io/crates/html-to-markdown-rs">
@@ -153,14 +153,13 @@ The dispatcher is invisible to the caller. Output is byte-identical across tiers
 
 **`ConversionOptions`** – Key configuration fields:
 
-- `heading_style`: Heading format (`"underlined"` | `"atx"` | `"atx_closed"`) — default: `"underlined"`
+- `heading_style`: Heading format (`"underlined"` | `"atx"` | `"atx_closed"`) — default: `"atx"`
 - `list_indent_width`: Spaces per indent level — default: `2`
-- `bullets`: Bullet characters cycle — default: `"*+-"`
+- `bullets`: Bullet characters cycle — default: `"-*+"`
 - `wrap`: Enable text wrapping — default: `false`
 - `wrap_width`: Wrap at column — default: `80`
 - `code_language`: Default fenced code block language — default: none
-- `extract_metadata`: Enable metadata extraction into `result.metadata` — default: `false`
-- `extract_tables`: Enable structured table extraction into `result.tables` — default: `false`
+- `extract_metadata`: Enable metadata extraction into `result.metadata` — default: `true`
 - `output_format`: Output markup format (`"markdown"` | `"djot"` | `"plain"`) — default: `"markdown"`
 
 ## Djot Output Format
@@ -214,13 +213,13 @@ The metadata extraction feature enables comprehensive document analysis during c
 
 ## Part of Kreuzberg.dev
 
-- [Kreuzberg](https://github.com/kreuzberg-dev/kreuzberg) — document intelligence: text, tables, metadata from 90+ formats with optional OCR.
+- [Kreuzberg](https://github.com/kreuzberg-dev/kreuzberg) — document intelligence: text, tables, metadata from 91+ formats with optional OCR.
 - [Kreuzberg Cloud](https://github.com/kreuzberg-dev/kreuzberg-cloud) — managed extraction API with SDKs, dashboards, and observability.
 - [kreuzcrawl](https://github.com/kreuzberg-dev/kreuzcrawl) — web crawling and scraping with HTML→Markdown and headless-Chrome fallback.
+- [html-to-markdown](https://github.com/kreuzberg-dev/html-to-markdown) — fast, lossless HTML→Markdown engine.
 - [liter-llm](https://github.com/kreuzberg-dev/liter-llm) — universal LLM API client with native bindings for 14 languages and 143 providers.
 - [tree-sitter-language-pack](https://github.com/kreuzberg-dev/tree-sitter-language-pack) — tree-sitter grammars and code-intelligence primitives.
 - [alef](https://github.com/kreuzberg-dev/alef) — the polyglot binding generator that produces every per-language binding across the 5 polyglot repos.
-- [Discord](https://discord.gg/xt9WY3GnKR) — community, roadmap, announcements.
 
 ## Contributing
 
@@ -248,5 +247,4 @@ If you find this library useful, consider [sponsoring the project](https://githu
 Have questions or run into issues? We're here to help:
 
 - **GitHub Issues:** [github.com/kreuzberg-dev/html-to-markdown/issues](https://github.com/kreuzberg-dev/html-to-markdown/issues)
-- **Issues:** [github.com/kreuzberg-dev/html-to-markdown/issues](https://github.com/kreuzberg-dev/html-to-markdown/issues)
 - **Discord Community:** [discord.gg/xt9WY3GnKR](https://discord.gg/xt9WY3GnKR)

package/pkg/nodejs/html_to_markdown_wasm.d.ts

@@ -608,8 +608,7 @@ export class WasmNodeContext {
     /**
      * Construct a `NodeContext` with an owned attribute map.
      *
-     * Prefer `NodeContext.with_lazy_attributes` (pub(crate)) inside the
-     * converter to avoid the eager `collect_tag_attributes` allocation.
+     * Use this when the caller already has materialized attributes.
      */
     static withOwnedAttributes(node_type: WasmNodeType, tag_name: string, attributes: any, depth: number, index_in_parent: number, parent_tag: string | null | undefined, is_inline: boolean): WasmNodeContext;
     depth: number;
@@ -869,8 +868,7 @@ export class WasmTableGrid {
  * similar — that spans a contiguous run of bytes inside `DocumentNode.content`'s text field.
  *
  * Byte offsets (`start`..`end`) are into the UTF-8 encoded text of the parent node. The range
- * follows Rust slice conventions: `start` is inclusive and `end` is exclusive, so the annotated
- * text is `text[start as usize..end as usize]`.
+ * is half-open: `start` is inclusive and `end` is exclusive.
  *
  * Multiple annotations on the same node can overlap (e.g. bold-italic text), and they are
  * stored in the order they are encountered during DOM traversal.
@@ -987,9 +985,9 @@ export enum WasmWhitespaceMode {
  * # Arguments
  *
  * * `html` — the HTML string to convert.
- * * `options` — conversion options. Rust accepts either bare
- *   `ConversionOptions`, `Some(options)`, or `None`; bindings expose the same
- *   option fields through language-native constructors or optional parameters.
+ * * `options` — conversion options. Rust accepts bare `ConversionOptions`,
+ *   `Some(options)`, or `None`. Language bindings expose the same option
+ *   fields through native constructors or optional parameters.
  *
  * # Example
  *

package/pkg/nodejs/html_to_markdown_wasm.js

@@ -4598,8 +4598,7 @@ class WasmNodeContext {
     /**
      * Construct a `NodeContext` with an owned attribute map.
      *
-     * Prefer `NodeContext.with_lazy_attributes` (pub(crate)) inside the
-     * converter to avoid the eager `collect_tag_attributes` allocation.
+     * Use this when the caller already has materialized attributes.
      * @param {WasmNodeType} node_type
      * @param {string} tag_name
      * @param {any} attributes
@@ -5423,8 +5422,7 @@ exports.WasmTableGrid = WasmTableGrid;
  * similar — that spans a contiguous run of bytes inside `DocumentNode.content`'s text field.
  *
  * Byte offsets (`start`..`end`) are into the UTF-8 encoded text of the parent node. The range
- * follows Rust slice conventions: `start` is inclusive and `end` is exclusive, so the annotated
- * text is `text[start as usize..end as usize]`.
+ * is half-open: `start` is inclusive and `end` is exclusive.
  *
  * Multiple annotations on the same node can overlap (e.g. bold-italic text), and they are
  * stored in the order they are encountered during DOM traversal.
@@ -5651,9 +5649,9 @@ exports.WasmWhitespaceMode = WasmWhitespaceMode;
  * # Arguments
  *
  * * `html` — the HTML string to convert.
- * * `options` — conversion options. Rust accepts either bare
- *   `ConversionOptions`, `Some(options)`, or `None`; bindings expose the same
- *   option fields through language-native constructors or optional parameters.
+ * * `options` — conversion options. Rust accepts bare `ConversionOptions`,
+ *   `Some(options)`, or `None`. Language bindings expose the same option
+ *   fields through native constructors or optional parameters.
  *
  * # Example
  *

package/pkg/nodejs/package.json

@@ -1,7 +1,7 @@
 {
   "name": "html-to-markdown-wasm",
   "description": "High-performance HTML to Markdown converter",
-  "version": "3.6.10",
+  "version": "3.6.12",
   "license": "MIT",
   "repository": {
     "type": "git",

package/pkg/web/README.md

@@ -2,7 +2,7 @@
 
 <div align="center" style="display: flex; flex-wrap: wrap; gap: 8px; justify-content: center; margin: 20px 0;">
   <a href="https://github.com/kreuzberg-dev/alef">
-    <img src="https://img.shields.io/badge/Bindings-alef%20%D7%90-007ec6" alt="Bindings">
+    <img src="https://img.shields.io/badge/built%20with-alef%20%D7%90-007ec6" alt="Built with alef">
   </a>
   <!-- Language Bindings -->
   <a href="https://crates.io/crates/html-to-markdown-rs">
@@ -153,14 +153,13 @@ The dispatcher is invisible to the caller. Output is byte-identical across tiers
 
 **`ConversionOptions`** – Key configuration fields:
 
-- `heading_style`: Heading format (`"underlined"` | `"atx"` | `"atx_closed"`) — default: `"underlined"`
+- `heading_style`: Heading format (`"underlined"` | `"atx"` | `"atx_closed"`) — default: `"atx"`
 - `list_indent_width`: Spaces per indent level — default: `2`
-- `bullets`: Bullet characters cycle — default: `"*+-"`
+- `bullets`: Bullet characters cycle — default: `"-*+"`
 - `wrap`: Enable text wrapping — default: `false`
 - `wrap_width`: Wrap at column — default: `80`
 - `code_language`: Default fenced code block language — default: none
-- `extract_metadata`: Enable metadata extraction into `result.metadata` — default: `false`
-- `extract_tables`: Enable structured table extraction into `result.tables` — default: `false`
+- `extract_metadata`: Enable metadata extraction into `result.metadata` — default: `true`
 - `output_format`: Output markup format (`"markdown"` | `"djot"` | `"plain"`) — default: `"markdown"`
 
 ## Djot Output Format
@@ -214,13 +213,13 @@ The metadata extraction feature enables comprehensive document analysis during c
 
 ## Part of Kreuzberg.dev
 
-- [Kreuzberg](https://github.com/kreuzberg-dev/kreuzberg) — document intelligence: text, tables, metadata from 90+ formats with optional OCR.
+- [Kreuzberg](https://github.com/kreuzberg-dev/kreuzberg) — document intelligence: text, tables, metadata from 91+ formats with optional OCR.
 - [Kreuzberg Cloud](https://github.com/kreuzberg-dev/kreuzberg-cloud) — managed extraction API with SDKs, dashboards, and observability.
 - [kreuzcrawl](https://github.com/kreuzberg-dev/kreuzcrawl) — web crawling and scraping with HTML→Markdown and headless-Chrome fallback.
+- [html-to-markdown](https://github.com/kreuzberg-dev/html-to-markdown) — fast, lossless HTML→Markdown engine.
 - [liter-llm](https://github.com/kreuzberg-dev/liter-llm) — universal LLM API client with native bindings for 14 languages and 143 providers.
 - [tree-sitter-language-pack](https://github.com/kreuzberg-dev/tree-sitter-language-pack) — tree-sitter grammars and code-intelligence primitives.
 - [alef](https://github.com/kreuzberg-dev/alef) — the polyglot binding generator that produces every per-language binding across the 5 polyglot repos.
-- [Discord](https://discord.gg/xt9WY3GnKR) — community, roadmap, announcements.
 
 ## Contributing
 
@@ -248,5 +247,4 @@ If you find this library useful, consider [sponsoring the project](https://githu
 Have questions or run into issues? We're here to help:
 
 - **GitHub Issues:** [github.com/kreuzberg-dev/html-to-markdown/issues](https://github.com/kreuzberg-dev/html-to-markdown/issues)
-- **Issues:** [github.com/kreuzberg-dev/html-to-markdown/issues](https://github.com/kreuzberg-dev/html-to-markdown/issues)
 - **Discord Community:** [discord.gg/xt9WY3GnKR](https://discord.gg/xt9WY3GnKR)

package/pkg/web/html_to_markdown_wasm.d.ts

@@ -608,8 +608,7 @@ export class WasmNodeContext {
     /**
      * Construct a `NodeContext` with an owned attribute map.
      *
-     * Prefer `NodeContext.with_lazy_attributes` (pub(crate)) inside the
-     * converter to avoid the eager `collect_tag_attributes` allocation.
+     * Use this when the caller already has materialized attributes.
      */
     static withOwnedAttributes(node_type: WasmNodeType, tag_name: string, attributes: any, depth: number, index_in_parent: number, parent_tag: string | null | undefined, is_inline: boolean): WasmNodeContext;
     depth: number;
@@ -869,8 +868,7 @@ export class WasmTableGrid {
  * similar — that spans a contiguous run of bytes inside `DocumentNode.content`'s text field.
  *
  * Byte offsets (`start`..`end`) are into the UTF-8 encoded text of the parent node. The range
- * follows Rust slice conventions: `start` is inclusive and `end` is exclusive, so the annotated
- * text is `text[start as usize..end as usize]`.
+ * is half-open: `start` is inclusive and `end` is exclusive.
  *
  * Multiple annotations on the same node can overlap (e.g. bold-italic text), and they are
  * stored in the order they are encountered during DOM traversal.
@@ -987,9 +985,9 @@ export enum WasmWhitespaceMode {
  * # Arguments
  *
  * * `html` — the HTML string to convert.
- * * `options` — conversion options. Rust accepts either bare
- *   `ConversionOptions`, `Some(options)`, or `None`; bindings expose the same
- *   option fields through language-native constructors or optional parameters.
+ * * `options` — conversion options. Rust accepts bare `ConversionOptions`,
+ *   `Some(options)`, or `None`. Language bindings expose the same option
+ *   fields through native constructors or optional parameters.
  *
  * # Example
  *

package/pkg/web/html_to_markdown_wasm.js

@@ -4575,8 +4575,7 @@ export class WasmNodeContext {
     /**
      * Construct a `NodeContext` with an owned attribute map.
      *
-     * Prefer `NodeContext.with_lazy_attributes` (pub(crate)) inside the
-     * converter to avoid the eager `collect_tag_attributes` allocation.
+     * Use this when the caller already has materialized attributes.
      * @param {WasmNodeType} node_type
      * @param {string} tag_name
      * @param {any} attributes
@@ -5389,8 +5388,7 @@ if (Symbol.dispose) WasmTableGrid.prototype[Symbol.dispose] = WasmTableGrid.prot
  * similar — that spans a contiguous run of bytes inside `DocumentNode.content`'s text field.
  *
  * Byte offsets (`start`..`end`) are into the UTF-8 encoded text of the parent node. The range
- * follows Rust slice conventions: `start` is inclusive and `end` is exclusive, so the annotated
- * text is `text[start as usize..end as usize]`.
+ * is half-open: `start` is inclusive and `end` is exclusive.
  *
  * Multiple annotations on the same node can overlap (e.g. bold-italic text), and they are
  * stored in the order they are encountered during DOM traversal.
@@ -5609,9 +5607,9 @@ export const WasmWhitespaceMode = Object.freeze({
  * # Arguments
  *
  * * `html` — the HTML string to convert.
- * * `options` — conversion options. Rust accepts either bare
- *   `ConversionOptions`, `Some(options)`, or `None`; bindings expose the same
- *   option fields through language-native constructors or optional parameters.
+ * * `options` — conversion options. Rust accepts bare `ConversionOptions`,
+ *   `Some(options)`, or `None`. Language bindings expose the same option
+ *   fields through native constructors or optional parameters.
  *
  * # Example
  *

package/pkg/web/package.json

@@ -2,7 +2,7 @@
   "name": "html-to-markdown-wasm",
   "type": "module",
   "description": "High-performance HTML to Markdown converter",
-  "version": "3.6.10",
+  "version": "3.6.12",
   "license": "MIT",
   "repository": {
     "type": "git",