@kreuzberg/html-to-markdown-wasm 3.6.0-rc.9 → 3.6.0

package/pkg/web/html_to_markdown_wasm.js

@@ -4376,7 +4376,21 @@ if (Symbol.dispose) WasmNodeContent.prototype[Symbol.dispose] = WasmNodeContent.
  * Context information passed to all visitor methods.
  *
  * Provides comprehensive metadata about the current node being visited,
- * including its type, attributes, position in the DOM tree, and parent context.
+ * including its type, tag name, position in the DOM tree, and parent context.
+ *
+ * ## Attributes
+ *
+ * Access attributes via `NodeContext.attributes`, which returns
+ * `&BTreeMap<String, String>`. When the context was built with
+ * `NodeContext.with_lazy_attributes` (the hot path inside the converter),
+ * the map is only materialized on the first call — if the visitor never reads
+ * attributes, the allocation is skipped.
+ *
+ * ## Lifetimes
+ *
+ * String fields use `Cow<'_, str>` so the converter can pass slices directly
+ * out of the parsed DOM without allocating. Visitor implementations that need
+ * to outlive the callback should call `NodeContext.into_owned`.
  */
 export class WasmNodeContext {
     static __wrap(ptr) {
@@ -4396,9 +4410,14 @@ export class WasmNodeContext {
         wasm.__wbg_wasmnodecontext_free(ptr, 0);
     }
     /**
+     * Return a reference to the attribute map.
+     *
+     * If the context was built with `NodeContext.with_lazy_attributes`, the
+     * map is materialized on the first call and cached for subsequent calls.
+     * If this method is never called, no allocation occurs for attributes.
      * @returns {any}
      */
-    get attributes() {
+    attributes() {
         const ret = wasm.wasmnodecontext_attributes(this.__wbg_ptr);
         return takeObject(ret);
     }
@@ -4423,6 +4442,14 @@ export class WasmNodeContext {
         const ret = wasm.wasmnodecontext_indexInParent(this.__wbg_ptr);
         return ret >>> 0;
     }
+    /**
+     * Promote any borrowed fields into owned storage so the context can outlive `'a`.
+     * @returns {WasmNodeContext}
+     */
+    intoOwned() {
+        const ret = wasm.wasmnodecontext_intoOwned(this.__wbg_ptr);
+        return WasmNodeContext.__wrap(ret);
+    }
     /**
      * @returns {boolean}
      */
@@ -4433,18 +4460,17 @@ export class WasmNodeContext {
     /**
      * @param {WasmNodeType} nodeType
      * @param {string} tagName
-     * @param {any} attributes
      * @param {number} depth
      * @param {number} indexInParent
      * @param {boolean} isInline
      * @param {string | null} [parentTag]
      */
-    constructor(nodeType, tagName, attributes, depth, indexInParent, isInline, parentTag) {
+    constructor(nodeType, tagName, depth, indexInParent, isInline, parentTag) {
         const ptr0 = passStringToWasm0(tagName, wasm.__wbindgen_export, wasm.__wbindgen_export2);
         const len0 = WASM_VECTOR_LEN;
         var ptr1 = isLikeNone(parentTag) ? 0 : passStringToWasm0(parentTag, wasm.__wbindgen_export, wasm.__wbindgen_export2);
         var len1 = WASM_VECTOR_LEN;
-        const ret = wasm.wasmnodecontext_new(nodeType, ptr0, len0, addHeapObject(attributes), depth, indexInParent, isInline, ptr1, len1);
+        const ret = wasm.wasmnodecontext_new(nodeType, ptr0, len0, depth, indexInParent, isInline, ptr1, len1);
         this.__wbg_ptr = ret;
         WasmNodeContextFinalization.register(this, this.__wbg_ptr, this);
         return this;
@@ -4487,12 +4513,6 @@ export class WasmNodeContext {
             wasm.__wbindgen_add_to_stack_pointer(16);
         }
     }
-    /**
-     * @param {any} value
-     */
-    set attributes(value) {
-        wasm.wasmnodecontext_set_attributes(this.__wbg_ptr, addHeapObject(value));
-    }
     /**
      * @param {number} value
      */
@@ -4552,6 +4572,28 @@ export class WasmNodeContext {
             wasm.__wbindgen_export4(deferred1_0, deferred1_1, 1);
         }
     }
+    /**
+     * 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.
+     * @param {WasmNodeType} node_type
+     * @param {string} tag_name
+     * @param {any} attributes
+     * @param {number} depth
+     * @param {number} index_in_parent
+     * @param {string | null | undefined} parent_tag
+     * @param {boolean} is_inline
+     * @returns {WasmNodeContext}
+     */
+    static withOwnedAttributes(node_type, tag_name, attributes, depth, index_in_parent, parent_tag, is_inline) {
+        const ptr0 = passStringToWasm0(tag_name, wasm.__wbindgen_export, wasm.__wbindgen_export2);
+        const len0 = WASM_VECTOR_LEN;
+        var ptr1 = isLikeNone(parent_tag) ? 0 : passStringToWasm0(parent_tag, wasm.__wbindgen_export, wasm.__wbindgen_export2);
+        var len1 = WASM_VECTOR_LEN;
+        const ret = wasm.wasmnodecontext_withOwnedAttributes(node_type, ptr0, len0, addHeapObject(attributes), depth, index_in_parent, ptr1, len1, is_inline);
+        return WasmNodeContext.__wrap(ret);
+    }
 }
 if (Symbol.dispose) WasmNodeContext.prototype[Symbol.dispose] = WasmNodeContext.prototype.free;
 
@@ -5008,7 +5050,7 @@ export class WasmProcessingWarning {
 if (Symbol.dispose) WasmProcessingWarning.prototype[Symbol.dispose] = WasmProcessingWarning.prototype.free;
 
 /**
- * Structured data block (JSON-LD, Microdata, or RDFa).
+ * Structured data block (JSON-LD, Microdata, or `RDFa`).
  *
  * Represents machine-readable structured data found in the document.
  * JSON-LD blocks are collected as raw JSON strings for flexibility.
@@ -5606,20 +5648,46 @@ export function convert(html, options) {
 function __wbg_get_imports() {
     const import0 = {
         __proto__: null,
-        __wbg___wbindgen_is_function_754e9f305ff6029e: function(arg0) {
+        __wbg_Error_9dc85fe1bc224456: function(arg0, arg1) {
+            const ret = Error(getStringFromWasm0(arg0, arg1));
+            return addHeapObject(ret);
+        },
+        __wbg___wbindgen_boolean_get_b131b2f36d6b2f55: function(arg0) {
+            const v = getObject(arg0);
+            const ret = typeof(v) === 'boolean' ? v : undefined;
+            return isLikeNone(ret) ? 0xFFFFFF : ret ? 1 : 0;
+        },
+        __wbg___wbindgen_debug_string_56c147eb1a51f0c4: function(arg0, arg1) {
+            const ret = debugString(getObject(arg1));
+            const ptr1 = passStringToWasm0(ret, wasm.__wbindgen_export, wasm.__wbindgen_export2);
+            const len1 = WASM_VECTOR_LEN;
+            getDataViewMemory0().setInt32(arg0 + 4 * 1, len1, true);
+            getDataViewMemory0().setInt32(arg0 + 4 * 0, ptr1, true);
+        },
+        __wbg___wbindgen_is_function_147961669f068cd4: function(arg0) {
             const ret = typeof(getObject(arg0)) === 'function';
             return ret;
         },
-        __wbg___wbindgen_is_object_56732c2bc353f41d: function(arg0) {
+        __wbg___wbindgen_is_object_3a2c414391dbf751: function(arg0) {
             const val = getObject(arg0);
             const ret = typeof(val) === 'object' && val !== null;
             return ret;
         },
-        __wbg___wbindgen_is_undefined_67b456be8673d3d7: function(arg0) {
+        __wbg___wbindgen_is_undefined_4410e3c20a99fa97: function(arg0) {
             const ret = getObject(arg0) === undefined;
             return ret;
         },
-        __wbg___wbindgen_string_get_72bdf95d3ae505b1: function(arg0, arg1) {
+        __wbg___wbindgen_jsval_loose_eq_e07e3b1f5db6da6c: function(arg0, arg1) {
+            const ret = getObject(arg0) == getObject(arg1);
+            return ret;
+        },
+        __wbg___wbindgen_number_get_588ed6b97f0d7e14: function(arg0, arg1) {
+            const obj = getObject(arg1);
+            const ret = typeof(obj) === 'number' ? obj : undefined;
+            getDataViewMemory0().setFloat64(arg0 + 8 * 1, isLikeNone(ret) ? 0 : ret, true);
+            getDataViewMemory0().setInt32(arg0 + 4 * 0, !isLikeNone(ret), true);
+        },
+        __wbg___wbindgen_string_get_fa2687d531ed17a5: function(arg0, arg1) {
             const obj = getObject(arg1);
             const ret = typeof(obj) === 'string' ? obj : undefined;
             var ptr1 = isLikeNone(ret) ? 0 : passStringToWasm0(ret, wasm.__wbindgen_export, wasm.__wbindgen_export2);
@@ -5627,47 +5695,126 @@ function __wbg_get_imports() {
             getDataViewMemory0().setInt32(arg0 + 4 * 1, len1, true);
             getDataViewMemory0().setInt32(arg0 + 4 * 0, ptr1, true);
         },
-        __wbg___wbindgen_throw_1506f2235d1bdba0: function(arg0, arg1) {
+        __wbg___wbindgen_throw_bbadd78c1bac3a77: function(arg0, arg1) {
             throw new Error(getStringFromWasm0(arg0, arg1));
         },
-        __wbg_apply_292b6d94e4f92b15: function() { return handleError(function (arg0, arg1, arg2) {
+        __wbg_apply_5d99f956e2dda74d: function() { return handleError(function (arg0, arg1, arg2) {
             const ret = getObject(arg0).apply(getObject(arg1), getObject(arg2));
             return addHeapObject(ret);
         }, arguments); },
-        __wbg_get_de6a0f7d4d18a304: function() { return handleError(function (arg0, arg1) {
+        __wbg_call_91f00ddc43e01490: function() { return handleError(function (arg0, arg1) {
+            const ret = getObject(arg0).call(getObject(arg1));
+            return addHeapObject(ret);
+        }, arguments); },
+        __wbg_done_6a8439e544ec6206: function(arg0) {
+            const ret = getObject(arg0).done;
+            return ret;
+        },
+        __wbg_entries_5a6a7e7e0df09fe5: function(arg0) {
+            const ret = Object.entries(getObject(arg0));
+            return addHeapObject(ret);
+        },
+        __wbg_get_44e98e27bda25b5b: function() { return handleError(function (arg0, arg1) {
             const ret = Reflect.get(getObject(arg0), getObject(arg1));
             return addHeapObject(ret);
         }, arguments); },
-        __wbg_has_73740b27f436fed3: function() { return handleError(function (arg0, arg1) {
+        __wbg_get_4b90d6d8c5deb5d5: function(arg0, arg1) {
+            const ret = getObject(arg0)[arg1 >>> 0];
+            return addHeapObject(ret);
+        },
+        __wbg_get_52a8a619f7b88df6: function() { return handleError(function (arg0, arg1) {
+            const ret = Reflect.get(getObject(arg0), getObject(arg1));
+            return addHeapObject(ret);
+        }, arguments); },
+        __wbg_get_unchecked_46e778e3cec74b5e: function(arg0, arg1) {
+            const ret = getObject(arg0)[arg1 >>> 0];
+            return addHeapObject(ret);
+        },
+        __wbg_has_14676d88c1340d2c: function() { return handleError(function (arg0, arg1) {
             const ret = Reflect.has(getObject(arg0), getObject(arg1));
             return ret;
         }, arguments); },
-        __wbg_new_ce1ab61c1c2b300d: function() {
-            const ret = new Object();
+        __wbg_instanceof_ArrayBuffer_a581da923203f29f: function(arg0) {
+            let result;
+            try {
+                result = getObject(arg0) instanceof ArrayBuffer;
+            } catch (_) {
+                result = false;
+            }
+            const ret = result;
+            return ret;
+        },
+        __wbg_instanceof_Uint8Array_b6fe1ac89eba107e: function(arg0) {
+            let result;
+            try {
+                result = getObject(arg0) instanceof Uint8Array;
+            } catch (_) {
+                result = false;
+            }
+            const ret = result;
+            return ret;
+        },
+        __wbg_iterator_9b36cebf3be7b7cd: function() {
+            const ret = Symbol.iterator;
             return addHeapObject(ret);
         },
-        __wbg_new_d90091b82fdf5b91: function() {
+        __wbg_length_68a9d5278d084f4f: function(arg0) {
+            const ret = getObject(arg0).length;
+            return ret;
+        },
+        __wbg_length_fb04d16d7bdf6d4c: function(arg0) {
+            const ret = getObject(arg0).length;
+            return ret;
+        },
+        __wbg_new_0b303268aa395a38: function() {
             const ret = new Array();
             return addHeapObject(ret);
         },
-        __wbg_parse_03863847d06c4e89: function() { return handleError(function (arg0, arg1) {
+        __wbg_new_20b778a4c5c691c3: function() {
+            const ret = new Object();
+            return addHeapObject(ret);
+        },
+        __wbg_new_883c0db065f06efd: function() {
+            const ret = new Map();
+            return addHeapObject(ret);
+        },
+        __wbg_new_b06772b280cc6e52: function(arg0) {
+            const ret = new Uint8Array(getObject(arg0));
+            return addHeapObject(ret);
+        },
+        __wbg_next_8cb028b6ba50743f: function() { return handleError(function (arg0) {
+            const ret = getObject(arg0).next();
+            return addHeapObject(ret);
+        }, arguments); },
+        __wbg_next_cfd0b146c9538df8: function(arg0) {
+            const ret = getObject(arg0).next;
+            return addHeapObject(ret);
+        },
+        __wbg_parse_246201845d0eb98c: function() { return handleError(function (arg0, arg1) {
             const ret = JSON.parse(getStringFromWasm0(arg0, arg1));
             return addHeapObject(ret);
         }, arguments); },
-        __wbg_push_a6822215aa43e71c: function(arg0, arg1) {
+        __wbg_prototypesetcall_956c7493c68e29b4: function(arg0, arg1, arg2) {
+            Uint8Array.prototype.set.call(getArrayU8FromWasm0(arg0, arg1), getObject(arg2));
+        },
+        __wbg_push_ceb8ef046afb2041: function(arg0, arg1) {
             const ret = getObject(arg0).push(getObject(arg1));
             return ret;
         },
         __wbg_set_6be42768c690e380: function(arg0, arg1, arg2) {
             getObject(arg0)[takeObject(arg1)] = takeObject(arg2);
         },
-        __wbg_set_6e30c9374c26414c: function() { return handleError(function (arg0, arg1, arg2) {
+        __wbg_set_a6ba3ac0e634b822: function() { return handleError(function (arg0, arg1, arg2) {
             const ret = Reflect.set(getObject(arg0), getObject(arg1), getObject(arg2));
             return ret;
         }, arguments); },
-        __wbg_set_dca99999bba88a9a: function(arg0, arg1, arg2) {
+        __wbg_set_da33c120a6584674: function(arg0, arg1, arg2) {
             getObject(arg0)[arg1 >>> 0] = takeObject(arg2);
         },
+        __wbg_value_3d3defe09fb1ffca: function(arg0) {
+            const ret = getObject(arg0).value;
+            return addHeapObject(ret);
+        },
         __wbg_wasmdocumentnode_new: function(arg0) {
             const ret = WasmDocumentNode.__wrap(arg0);
             return addHeapObject(ret);
@@ -5860,6 +6007,71 @@ function _assertClass(instance, klass) {
     }
 }
 
+function debugString(val) {
+    // primitive types
+    const type = typeof val;
+    if (type == 'number' || type == 'boolean' || val == null) {
+        return  `${val}`;
+    }
+    if (type == 'string') {
+        return `"${val}"`;
+    }
+    if (type == 'symbol') {
+        const description = val.description;
+        if (description == null) {
+            return 'Symbol';
+        } else {
+            return `Symbol(${description})`;
+        }
+    }
+    if (type == 'function') {
+        const name = val.name;
+        if (typeof name == 'string' && name.length > 0) {
+            return `Function(${name})`;
+        } else {
+            return 'Function';
+        }
+    }
+    // objects
+    if (Array.isArray(val)) {
+        const length = val.length;
+        let debug = '[';
+        if (length > 0) {
+            debug += debugString(val[0]);
+        }
+        for(let i = 1; i < length; i++) {
+            debug += ', ' + debugString(val[i]);
+        }
+        debug += ']';
+        return debug;
+    }
+    // Test for built-in
+    const builtInMatches = /\[object ([^\]]+)\]/.exec(toString.call(val));
+    let className;
+    if (builtInMatches && builtInMatches.length > 1) {
+        className = builtInMatches[1];
+    } else {
+        // Failed to match the standard '[object ClassName]'
+        return toString.call(val);
+    }
+    if (className == 'Object') {
+        // we're a user defined class or Object
+        // JSON.stringify avoids problems with cycles, and is generally much
+        // easier than looping through ownProperties of `val`.
+        try {
+            return 'Object(' + JSON.stringify(val) + ')';
+        } catch (_) {
+            return 'Object';
+        }
+    }
+    // errors
+    if (val instanceof Error) {
+        return `${val.name}: ${val.message}\n${val.stack}`;
+    }
+    // TODO we could test for more things here, like `Set`s and `Map`s.
+    return className;
+}
+
 function dropObject(idx) {
     if (idx < 1028) return;
     heap[idx] = heap_next;
@@ -5881,6 +6093,11 @@ function getArrayU32FromWasm0(ptr, len) {
     return getUint32ArrayMemory0().subarray(ptr / 4, ptr / 4 + len);
 }
 
+function getArrayU8FromWasm0(ptr, len) {
+    ptr = ptr >>> 0;
+    return getUint8ArrayMemory0().subarray(ptr / 1, ptr / 1 + len);
+}
+
 let cachedDataViewMemory0 = null;
 function getDataViewMemory0() {
     if (cachedDataViewMemory0 === null || cachedDataViewMemory0.buffer.detached === true || (cachedDataViewMemory0.buffer.detached === undefined && cachedDataViewMemory0.buffer !== wasm.memory.buffer)) {

package/pkg/web/html_to_markdown_wasm_bg.wasm.d.ts

@@ -16,7 +16,6 @@ export const __wbg_wasmimagemetadata_free: (a: number, b: number) => void;
 export const __wbg_wasmlinkmetadata_free: (a: number, b: number) => void;
 export const __wbg_wasmmetadataentry_free: (a: number, b: number) => void;
 export const __wbg_wasmnodecontent_free: (a: number, b: number) => void;
-export const __wbg_wasmnodecontext_free: (a: number, b: number) => void;
 export const __wbg_wasmpreprocessingoptions_free: (a: number, b: number) => void;
 export const __wbg_wasmprocessingwarning_free: (a: number, b: number) => void;
 export const __wbg_wasmstructureddata_free: (a: number, b: number) => void;
@@ -378,18 +377,13 @@ export const wasmnodecontent_term: (a: number, b: number) => void;
 export const wasmnodecontent_text: (a: number, b: number) => void;
 export const wasmnodecontext_attributes: (a: number) => number;
 export const wasmnodecontext_default: () => number;
-export const wasmnodecontext_indexInParent: (a: number) => number;
+export const wasmnodecontext_intoOwned: (a: number) => number;
 export const wasmnodecontext_isInline: (a: number) => number;
-export const wasmnodecontext_new: (a: number, b: number, c: number, d: number, e: number, f: number, g: number, h: number, i: number) => number;
+export const wasmnodecontext_new: (a: number, b: number, c: number, d: number, e: number, f: number, g: number, h: number) => number;
 export const wasmnodecontext_nodeType: (a: number, b: number) => void;
-export const wasmnodecontext_parentTag: (a: number, b: number) => void;
-export const wasmnodecontext_set_attributes: (a: number, b: number) => void;
-export const wasmnodecontext_set_indexInParent: (a: number, b: number) => void;
 export const wasmnodecontext_set_isInline: (a: number, b: number) => void;
 export const wasmnodecontext_set_nodeType: (a: number, b: number) => void;
-export const wasmnodecontext_set_parentTag: (a: number, b: number, c: number) => void;
-export const wasmnodecontext_set_tagName: (a: number, b: number, c: number) => void;
-export const wasmnodecontext_tagName: (a: number, b: number) => void;
+export const wasmnodecontext_withOwnedAttributes: (a: number, b: number, c: number, d: number, e: number, f: number, g: number, h: number, i: number) => number;
 export const wasmpreprocessingoptions_default: () => number;
 export const wasmpreprocessingoptions_enabled: (a: number) => number;
 export const wasmpreprocessingoptions_new: (a: number, b: number, c: number, d: number) => number;
@@ -443,6 +437,7 @@ export const wasmnodecontent_ordered: (a: number) => number;
 export const wasmnodecontent_new: () => number;
 export const wasmheadermetadata_set_depth: (a: number, b: number) => void;
 export const wasmnodecontext_set_depth: (a: number, b: number) => void;
+export const wasmnodecontext_set_indexInParent: (a: number, b: number) => void;
 export const wasmtablegrid_set_cols: (a: number, b: number) => void;
 export const wasmtablegrid_set_rows: (a: number, b: number) => void;
 export const wasmtextannotation_set_end: (a: number, b: number) => void;
@@ -450,13 +445,19 @@ export const wasmtextannotation_set_start: (a: number, b: number) => void;
 export const wasmnodecontent_set_imageIndex: (a: number, b: number) => void;
 export const wasmheadermetadata_depth: (a: number) => number;
 export const wasmnodecontext_depth: (a: number) => number;
+export const wasmnodecontext_indexInParent: (a: number) => number;
 export const wasmtablegrid_cols: (a: number) => number;
 export const wasmtablegrid_rows: (a: number) => number;
 export const wasmtextannotation_end: (a: number) => number;
 export const wasmtextannotation_start: (a: number) => number;
 export const wasmannotationkind_new: () => number;
+export const wasmnodecontext_parentTag: (a: number, b: number) => void;
 export const wasmnodecontent_set_ordered: (a: number, b: number) => void;
+export const wasmnodecontext_set_tagName: (a: number, b: number, c: number) => void;
+export const wasmnodecontext_set_parentTag: (a: number, b: number, c: number) => void;
+export const wasmnodecontext_tagName: (a: number, b: number) => void;
 export const wasmnodecontent_imageIndex: (a: number) => number;
+export const __wbg_wasmnodecontext_free: (a: number, b: number) => void;
 export const __wbg_wasmpreprocessingoptionsupdate_free: (a: number, b: number) => void;
 export const __wbindgen_export: (a: number, b: number) => number;
 export const __wbindgen_export2: (a: number, b: number, c: number, d: number) => number;

package/pkg/web/package.json

@@ -2,7 +2,7 @@
   "name": "html-to-markdown-wasm",
   "type": "module",
   "description": "High-performance HTML to Markdown converter",
-  "version": "3.6.0-rc.9",
+  "version": "3.6.0",
   "license": "MIT",
   "repository": {
     "type": "git",