@xberg-io/xberg-wasm 1.2.8 → 1.2.9

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@xberg-io/xberg-wasm",
-  "version": "1.2.8",
+  "version": "1.2.9",
   "private": false,
   "description": "High-performance document intelligence library",
   "license": "MIT",

package/pkg/web/package.json

@@ -2,7 +2,7 @@
   "name": "xberg-wasm",
   "type": "module",
   "description": "High-performance document intelligence library",
-  "version": "1.2.8",
+  "version": "1.2.9",
   "license": "MIT",
   "repository": {
     "type": "git",

package/pkg/web/xberg_wasm.d.ts

@@ -2527,17 +2527,28 @@ export class WasmExtractionConfig {
      * image I/O and processing when results won't be used.
      */
     needsImageProcessing(): boolean;
-    constructor(mimeDetectionPolicy?: WasmMimeDetectionPolicy | null, useCache?: boolean | null, enableQualityProcessing?: boolean | null, forceOcr?: boolean | null, ocrStrategy?: any | null, disableOcr?: boolean | null, resultFormat?: WasmResultFormat | null, outputFormat?: any | null, escapeMarkdown?: boolean | null, tableAnchors?: boolean | null, jupyterCellRendering?: WasmJupyterCellRendering | null, applyNotebookCellTags?: boolean | null, useLayoutForMarkdown?: boolean | null, includeDocumentStructure?: boolean | null, url?: WasmUrlExtractionConfig | null, maxArchiveDepth?: number | null, ocr?: WasmOcrConfig | null, forceOcrPages?: Uint32Array | null, chunking?: WasmChunkingConfig | null, contentFilter?: WasmContentFilterConfig | null, images?: WasmImageExtractionConfig | null, pdfOptions?: WasmPdfConfig | null, tokenReduction?: WasmTokenReductionOptions | null, languageDetection?: WasmLanguageDetectionConfig | null, pages?: WasmPageConfig | null, keywords?: WasmKeywordConfig | null, postprocessor?: WasmPostProcessorConfig | null, htmlOptions?: WasmConversionOptions | null, htmlOutput?: WasmHtmlOutputConfig | null, extractionTimeoutSecs?: bigint | null, maxConcurrentExtractions?: number | null, securityLimits?: WasmSecurityLimits | null, maxEmbeddedFileBytes?: bigint | null, layout?: WasmLayoutDetectionConfig | null, transcription?: WasmTranscriptionConfig | null, acceleration?: WasmAccelerationConfig | null, cacheNamespace?: string | null, cacheTtlSecs?: bigint | null, email?: WasmEmailConfig | null, csv?: WasmCsvConfig | null, geojson?: WasmGeoJsonExtractionConfig | null, concurrency?: WasmConcurrencyConfig | null, structuredExtraction?: WasmStructuredExtractionConfig | null, ner?: WasmNerConfig | null, redaction?: WasmRedactionConfig | null, summarization?: WasmSummarizationConfig | null, translation?: WasmTranslationConfig | null, pageClassification?: WasmPageClassificationConfig | null, chunkClassification?: WasmChunkClassificationConfig | null, captioning?: WasmCaptioningConfig | null, qrCodes?: boolean | null);
+    constructor(mimeDetectionPolicy?: WasmMimeDetectionPolicy | null, useCache?: boolean | null, enableQualityProcessing?: boolean | null, forceOcr?: boolean | null, ocrStrategy?: any | null, disableOcr?: boolean | null, resultFormat?: WasmResultFormat | null, outputFormat?: any | null, escapeMarkdown?: boolean | null, tableAnchors?: boolean | null, jupyterCellRendering?: WasmJupyterCellRendering | null, applyNotebookCellTags?: boolean | null, useLayoutForMarkdown?: boolean | null, includeDocumentStructure?: boolean | null, url?: WasmUrlExtractionConfig | null, maxArchiveDepth?: number | null, ocr?: WasmOcrConfig | null, forceOcrPages?: Uint32Array | null, ocrNearEmptyFallback?: boolean | null, ocrScannedPageQualityGate?: boolean | null, ocrEmbeddedImages?: boolean | null, chunking?: WasmChunkingConfig | null, contentFilter?: WasmContentFilterConfig | null, images?: WasmImageExtractionConfig | null, pdfOptions?: WasmPdfConfig | null, tokenReduction?: WasmTokenReductionOptions | null, languageDetection?: WasmLanguageDetectionConfig | null, pages?: WasmPageConfig | null, keywords?: WasmKeywordConfig | null, postprocessor?: WasmPostProcessorConfig | null, htmlOptions?: WasmConversionOptions | null, htmlOutput?: WasmHtmlOutputConfig | null, extractionTimeoutSecs?: bigint | null, maxConcurrentExtractions?: number | null, securityLimits?: WasmSecurityLimits | null, maxEmbeddedFileBytes?: bigint | null, layout?: WasmLayoutDetectionConfig | null, transcription?: WasmTranscriptionConfig | null, acceleration?: WasmAccelerationConfig | null, cacheNamespace?: string | null, cacheTtlSecs?: bigint | null, email?: WasmEmailConfig | null, csv?: WasmCsvConfig | null, geojson?: WasmGeoJsonExtractionConfig | null, concurrency?: WasmConcurrencyConfig | null, structuredExtraction?: WasmStructuredExtractionConfig | null, ner?: WasmNerConfig | null, redaction?: WasmRedactionConfig | null, summarization?: WasmSummarizationConfig | null, translation?: WasmTranslationConfig | null, pageClassification?: WasmPageClassificationConfig | null, chunkClassification?: WasmChunkClassificationConfig | null, captioning?: WasmCaptioningConfig | null, qrCodes?: boolean | null);
     /**
      * Whether embedded images get OCR'd.
      *
-     * This mirrors the condition the pipeline itself uses before it calls
-     * `image_ocr.process_images_with_ocr` (`core/pipeline/mod.rs`), and it is
-     * deliberately the same predicate rather than an equivalent one: when the
-     * two drifted apart, a container extractor asked `needs_image_data` and was
-     * told no, so it attached an image with an empty buffer, and the OCR path
-     * then ran on those zero bytes and reported `Could not determine image
-     * format` (GH#1662).
+     * This is THE condition -- `core/pipeline/mod.rs` and
+     * `extraction.image_ocr.process_images_with_ocr` both call this method rather than
+     * re-deriving it, because when two copies of it drifted apart a container extractor
+     * asked `needs_image_data` and was told no, so it attached an image with an empty
+     * buffer, and the OCR path then ran on those zero bytes and reported `Could not
+     * determine image format` (GH#1662). A re-derived copy anywhere reopens that defect;
+     * `embedded_image_ocr_gate_has_no_second_copy` in `core/pipeline/tests.rs` fails if
+     * one appears.
+     *
+     * `Self.ocr_embedded_images` is the caller's explicit answer to the OCR half;
+     * `None` derives it from whether an `ocr` block is present, which is what this
+     * condition was before GH#1752 gave the behaviour a setting of its own.
+     *
+     * `disable_ocr` still wins regardless: it is documented as skipping OCR "for all
+     * document types", and `ocr_embedded_images` (like the plain presence of an `ocr`
+     * block before it) is an AUTOMATIC trigger, not an explicit request like `force_ocr` --
+     * see `Self.effective_disable_ocr`'s callers elsewhere (`needs_image_processing`,
+     * `extractors/image.rs`, `engine/extract_impl.rs`) for the same precedent.
      */
     runsOcrOnEmbeddedImages(): boolean;
     /**
@@ -2639,6 +2650,12 @@ export class WasmExtractionConfig {
     set mimeDetectionPolicy(value: WasmMimeDetectionPolicy);
     get ner(): WasmNerConfig | undefined;
     set ner(value: WasmNerConfig | null | undefined);
+    get ocrEmbeddedImages(): boolean | undefined;
+    set ocrEmbeddedImages(value: boolean | null | undefined);
+    get ocrNearEmptyFallback(): boolean | undefined;
+    set ocrNearEmptyFallback(value: boolean | null | undefined);
+    get ocrScannedPageQualityGate(): boolean | undefined;
+    set ocrScannedPageQualityGate(value: boolean | null | undefined);
     ocrStrategy: any;
     get ocr(): WasmOcrConfig | undefined;
     set ocr(value: WasmOcrConfig | null | undefined);
@@ -9018,8 +9035,11 @@ export interface InitOutput {
     readonly wasmextractionconfig_needsImageData: (a: number) => number;
     readonly wasmextractionconfig_needsImageProcessing: (a: number) => number;
     readonly wasmextractionconfig_ner: (a: number) => number;
-    readonly wasmextractionconfig_new: (a: number, b: number, c: number, d: number, e: number, f: number, g: number, h: number, i: number, j: number, k: number, l: number, m: number, n: number, o: number, p: number, q: number, r: number, s: number, t: number, u: number, v: number, w: number, x: number, y: number, z: number, a1: number, b1: number, c1: number, d1: number, e1: number, f1: bigint, g1: number, h1: number, i1: number, j1: bigint, k1: number, l1: number, m1: number, n1: number, o1: number, p1: number, q1: bigint, r1: number, s1: number, t1: number, u1: number, v1: number, w1: number, x1: number, y1: number, z1: number, a2: number, b2: number, c2: number, d2: number) => number;
+    readonly wasmextractionconfig_new: (a: number, b: number, c: number, d: number, e: number, f: number, g: number, h: number, i: number, j: number, k: number, l: number, m: number, n: number, o: number, p: number, q: number, r: number, s: number, t: number, u: number, v: number, w: number, x: number, y: number, z: number, a1: number, b1: number, c1: number, d1: number, e1: number, f1: number, g1: number, h1: number, i1: bigint, j1: number, k1: number, l1: number, m1: bigint, n1: number, o1: number, p1: number, q1: number, r1: number, s1: number, t1: bigint, u1: number, v1: number, w1: number, x1: number, y1: number, z1: number, a2: number, b2: number, c2: number, d2: number, e2: number, f2: number, g2: number) => number;
     readonly wasmextractionconfig_ocr: (a: number) => number;
+    readonly wasmextractionconfig_ocrEmbeddedImages: (a: number) => number;
+    readonly wasmextractionconfig_ocrNearEmptyFallback: (a: number) => number;
+    readonly wasmextractionconfig_ocrScannedPageQualityGate: (a: number) => number;
     readonly wasmextractionconfig_ocrStrategy: (a: number) => any;
     readonly wasmextractionconfig_outputFormat: (a: number) => any;
     readonly wasmextractionconfig_pageClassification: (a: number) => number;
@@ -9063,6 +9083,9 @@ export interface InitOutput {
     readonly wasmextractionconfig_set_mimeDetectionPolicy: (a: number, b: number) => void;
     readonly wasmextractionconfig_set_ner: (a: number, b: number) => void;
     readonly wasmextractionconfig_set_ocr: (a: number, b: number) => void;
+    readonly wasmextractionconfig_set_ocrEmbeddedImages: (a: number, b: number) => void;
+    readonly wasmextractionconfig_set_ocrNearEmptyFallback: (a: number, b: number) => void;
+    readonly wasmextractionconfig_set_ocrScannedPageQualityGate: (a: number, b: number) => void;
     readonly wasmextractionconfig_set_ocrStrategy: (a: number, b: any) => void;
     readonly wasmextractionconfig_set_outputFormat: (a: number, b: any) => void;
     readonly wasmextractionconfig_set_pageClassification: (a: number, b: number) => void;

package/pkg/web/xberg_wasm.js

@@ -13946,6 +13946,9 @@ export class WasmExtractionConfig {
      * @param {number | null} [maxArchiveDepth]
      * @param {WasmOcrConfig | null} [ocr]
      * @param {Uint32Array | null} [forceOcrPages]
+     * @param {boolean | null} [ocrNearEmptyFallback]
+     * @param {boolean | null} [ocrScannedPageQualityGate]
+     * @param {boolean | null} [ocrEmbeddedImages]
      * @param {WasmChunkingConfig | null} [chunking]
      * @param {WasmContentFilterConfig | null} [contentFilter]
      * @param {WasmImageExtractionConfig | null} [images]
@@ -13980,7 +13983,7 @@ export class WasmExtractionConfig {
      * @param {WasmCaptioningConfig | null} [captioning]
      * @param {boolean | null} [qrCodes]
      */
-    constructor(mimeDetectionPolicy, useCache, enableQualityProcessing, forceOcr, ocrStrategy, disableOcr, resultFormat, outputFormat, escapeMarkdown, tableAnchors, jupyterCellRendering, applyNotebookCellTags, useLayoutForMarkdown, includeDocumentStructure, url, maxArchiveDepth, ocr, forceOcrPages, chunking, contentFilter, images, pdfOptions, tokenReduction, languageDetection, pages, keywords, postprocessor, htmlOptions, htmlOutput, extractionTimeoutSecs, maxConcurrentExtractions, securityLimits, maxEmbeddedFileBytes, layout, transcription, acceleration, cacheNamespace, cacheTtlSecs, email, csv, geojson, concurrency, structuredExtraction, ner, redaction, summarization, translation, pageClassification, chunkClassification, captioning, qrCodes) {
+    constructor(mimeDetectionPolicy, useCache, enableQualityProcessing, forceOcr, ocrStrategy, disableOcr, resultFormat, outputFormat, escapeMarkdown, tableAnchors, jupyterCellRendering, applyNotebookCellTags, useLayoutForMarkdown, includeDocumentStructure, url, maxArchiveDepth, ocr, forceOcrPages, ocrNearEmptyFallback, ocrScannedPageQualityGate, ocrEmbeddedImages, chunking, contentFilter, images, pdfOptions, tokenReduction, languageDetection, pages, keywords, postprocessor, htmlOptions, htmlOutput, extractionTimeoutSecs, maxConcurrentExtractions, securityLimits, maxEmbeddedFileBytes, layout, transcription, acceleration, cacheNamespace, cacheTtlSecs, email, csv, geojson, concurrency, structuredExtraction, ner, redaction, summarization, translation, pageClassification, chunkClassification, captioning, qrCodes) {
         let ptr0 = 0;
         if (!isLikeNone(url)) {
             _assertClass(url, WasmUrlExtractionConfig);
@@ -14130,11 +14133,32 @@ export class WasmExtractionConfig {
             _assertClass(captioning, WasmCaptioningConfig);
             ptr30 = captioning.__destroy_into_raw();
         }
-        const ret = wasm.wasmextractionconfig_new(isLikeNone(mimeDetectionPolicy) ? 3 : mimeDetectionPolicy, isLikeNone(useCache) ? 0xFFFFFF : useCache ? 1 : 0, isLikeNone(enableQualityProcessing) ? 0xFFFFFF : enableQualityProcessing ? 1 : 0, isLikeNone(forceOcr) ? 0xFFFFFF : forceOcr ? 1 : 0, isLikeNone(ocrStrategy) ? 0 : addToExternrefTable0(ocrStrategy), isLikeNone(disableOcr) ? 0xFFFFFF : disableOcr ? 1 : 0, isLikeNone(resultFormat) ? 2 : resultFormat, isLikeNone(outputFormat) ? 0 : addToExternrefTable0(outputFormat), isLikeNone(escapeMarkdown) ? 0xFFFFFF : escapeMarkdown ? 1 : 0, isLikeNone(tableAnchors) ? 0xFFFFFF : tableAnchors ? 1 : 0, isLikeNone(jupyterCellRendering) ? 3 : jupyterCellRendering, isLikeNone(applyNotebookCellTags) ? 0xFFFFFF : applyNotebookCellTags ? 1 : 0, isLikeNone(useLayoutForMarkdown) ? 0xFFFFFF : useLayoutForMarkdown ? 1 : 0, isLikeNone(includeDocumentStructure) ? 0xFFFFFF : includeDocumentStructure ? 1 : 0, ptr0, isLikeNone(maxArchiveDepth) ? Number.MAX_SAFE_INTEGER : (maxArchiveDepth) >>> 0, ptr1, ptr2, len2, ptr3, ptr4, ptr5, ptr6, ptr7, ptr8, ptr9, ptr10, ptr11, ptr12, ptr13, !isLikeNone(extractionTimeoutSecs), isLikeNone(extractionTimeoutSecs) ? BigInt(0) : extractionTimeoutSecs, isLikeNone(maxConcurrentExtractions) ? Number.MAX_SAFE_INTEGER : (maxConcurrentExtractions) >>> 0, ptr14, !isLikeNone(maxEmbeddedFileBytes), isLikeNone(maxEmbeddedFileBytes) ? BigInt(0) : maxEmbeddedFileBytes, ptr15, ptr16, ptr17, ptr18, len18, !isLikeNone(cacheTtlSecs), isLikeNone(cacheTtlSecs) ? BigInt(0) : cacheTtlSecs, ptr19, ptr20, ptr21, ptr22, ptr23, ptr24, ptr25, ptr26, ptr27, ptr28, ptr29, ptr30, isLikeNone(qrCodes) ? 0xFFFFFF : qrCodes ? 1 : 0);
+        const ret = wasm.wasmextractionconfig_new(isLikeNone(mimeDetectionPolicy) ? 3 : mimeDetectionPolicy, isLikeNone(useCache) ? 0xFFFFFF : useCache ? 1 : 0, isLikeNone(enableQualityProcessing) ? 0xFFFFFF : enableQualityProcessing ? 1 : 0, isLikeNone(forceOcr) ? 0xFFFFFF : forceOcr ? 1 : 0, isLikeNone(ocrStrategy) ? 0 : addToExternrefTable0(ocrStrategy), isLikeNone(disableOcr) ? 0xFFFFFF : disableOcr ? 1 : 0, isLikeNone(resultFormat) ? 2 : resultFormat, isLikeNone(outputFormat) ? 0 : addToExternrefTable0(outputFormat), isLikeNone(escapeMarkdown) ? 0xFFFFFF : escapeMarkdown ? 1 : 0, isLikeNone(tableAnchors) ? 0xFFFFFF : tableAnchors ? 1 : 0, isLikeNone(jupyterCellRendering) ? 3 : jupyterCellRendering, isLikeNone(applyNotebookCellTags) ? 0xFFFFFF : applyNotebookCellTags ? 1 : 0, isLikeNone(useLayoutForMarkdown) ? 0xFFFFFF : useLayoutForMarkdown ? 1 : 0, isLikeNone(includeDocumentStructure) ? 0xFFFFFF : includeDocumentStructure ? 1 : 0, ptr0, isLikeNone(maxArchiveDepth) ? Number.MAX_SAFE_INTEGER : (maxArchiveDepth) >>> 0, ptr1, ptr2, len2, isLikeNone(ocrNearEmptyFallback) ? 0xFFFFFF : ocrNearEmptyFallback ? 1 : 0, isLikeNone(ocrScannedPageQualityGate) ? 0xFFFFFF : ocrScannedPageQualityGate ? 1 : 0, isLikeNone(ocrEmbeddedImages) ? 0xFFFFFF : ocrEmbeddedImages ? 1 : 0, ptr3, ptr4, ptr5, ptr6, ptr7, ptr8, ptr9, ptr10, ptr11, ptr12, ptr13, !isLikeNone(extractionTimeoutSecs), isLikeNone(extractionTimeoutSecs) ? BigInt(0) : extractionTimeoutSecs, isLikeNone(maxConcurrentExtractions) ? Number.MAX_SAFE_INTEGER : (maxConcurrentExtractions) >>> 0, ptr14, !isLikeNone(maxEmbeddedFileBytes), isLikeNone(maxEmbeddedFileBytes) ? BigInt(0) : maxEmbeddedFileBytes, ptr15, ptr16, ptr17, ptr18, len18, !isLikeNone(cacheTtlSecs), isLikeNone(cacheTtlSecs) ? BigInt(0) : cacheTtlSecs, ptr19, ptr20, ptr21, ptr22, ptr23, ptr24, ptr25, ptr26, ptr27, ptr28, ptr29, ptr30, isLikeNone(qrCodes) ? 0xFFFFFF : qrCodes ? 1 : 0);
         this.__wbg_ptr = ret;
         WasmExtractionConfigFinalization.register(this, this.__wbg_ptr, this);
         return this;
     }
+    /**
+     * @returns {boolean | undefined}
+     */
+    get ocrEmbeddedImages() {
+        const ret = wasm.wasmextractionconfig_ocrEmbeddedImages(this.__wbg_ptr);
+        return ret === 0xFFFFFF ? undefined : ret !== 0;
+    }
+    /**
+     * @returns {boolean | undefined}
+     */
+    get ocrNearEmptyFallback() {
+        const ret = wasm.wasmextractionconfig_ocrNearEmptyFallback(this.__wbg_ptr);
+        return ret === 0xFFFFFF ? undefined : ret !== 0;
+    }
+    /**
+     * @returns {boolean | undefined}
+     */
+    get ocrScannedPageQualityGate() {
+        const ret = wasm.wasmextractionconfig_ocrScannedPageQualityGate(this.__wbg_ptr);
+        return ret === 0xFFFFFF ? undefined : ret !== 0;
+    }
     /**
      * @returns {any}
      */
@@ -14216,13 +14240,24 @@ export class WasmExtractionConfig {
     /**
      * Whether embedded images get OCR'd.
      *
-     * This mirrors the condition the pipeline itself uses before it calls
-     * `image_ocr.process_images_with_ocr` (`core/pipeline/mod.rs`), and it is
-     * deliberately the same predicate rather than an equivalent one: when the
-     * two drifted apart, a container extractor asked `needs_image_data` and was
-     * told no, so it attached an image with an empty buffer, and the OCR path
-     * then ran on those zero bytes and reported `Could not determine image
-     * format` (GH#1662).
+     * This is THE condition -- `core/pipeline/mod.rs` and
+     * `extraction.image_ocr.process_images_with_ocr` both call this method rather than
+     * re-deriving it, because when two copies of it drifted apart a container extractor
+     * asked `needs_image_data` and was told no, so it attached an image with an empty
+     * buffer, and the OCR path then ran on those zero bytes and reported `Could not
+     * determine image format` (GH#1662). A re-derived copy anywhere reopens that defect;
+     * `embedded_image_ocr_gate_has_no_second_copy` in `core/pipeline/tests.rs` fails if
+     * one appears.
+     *
+     * `Self.ocr_embedded_images` is the caller's explicit answer to the OCR half;
+     * `None` derives it from whether an `ocr` block is present, which is what this
+     * condition was before GH#1752 gave the behaviour a setting of its own.
+     *
+     * `disable_ocr` still wins regardless: it is documented as skipping OCR "for all
+     * document types", and `ocr_embedded_images` (like the plain presence of an `ocr`
+     * block before it) is an AUTOMATIC trigger, not an explicit request like `force_ocr` --
+     * see `Self.effective_disable_ocr`'s callers elsewhere (`needs_image_processing`,
+     * `extractors/image.rs`, `engine/extract_impl.rs`) for the same precedent.
      * @returns {boolean}
      */
     runsOcrOnEmbeddedImages() {
@@ -14506,6 +14541,24 @@ export class WasmExtractionConfig {
         }
         wasm.wasmextractionconfig_set_ner(this.__wbg_ptr, ptr0);
     }
+    /**
+     * @param {boolean | null} [value]
+     */
+    set ocrEmbeddedImages(value) {
+        wasm.wasmextractionconfig_set_ocrEmbeddedImages(this.__wbg_ptr, isLikeNone(value) ? 0xFFFFFF : value ? 1 : 0);
+    }
+    /**
+     * @param {boolean | null} [value]
+     */
+    set ocrNearEmptyFallback(value) {
+        wasm.wasmextractionconfig_set_ocrNearEmptyFallback(this.__wbg_ptr, isLikeNone(value) ? 0xFFFFFF : value ? 1 : 0);
+    }
+    /**
+     * @param {boolean | null} [value]
+     */
+    set ocrScannedPageQualityGate(value) {
+        wasm.wasmextractionconfig_set_ocrScannedPageQualityGate(this.__wbg_ptr, isLikeNone(value) ? 0xFFFFFF : value ? 1 : 0);
+    }
     /**
      * @param {any} value
      */
@@ -41590,7 +41643,7 @@ function __wbg_get_imports() {
             const ret = arg0.value;
             return ret;
         },
-        __wbg_warn_2e32b7c2f442f1f1: function(arg0, arg1) {
+        __wbg_warn_ef083b0b8c8c0df4: function(arg0, arg1) {
             console.warn(getStringFromWasm0(arg0, arg1));
         },
         __wbg_wasmarchiveentry_new: function(arg0) {

package/pkg/web/xberg_wasm_bg.wasm

@@ -1,4 +1,4 @@
 [diffend] Oversized file quarantined before diffing.
 name: package/pkg/web/xberg_wasm_bg.wasm
-size: 36042372 bytes
-sha256: d1d87906fc9e88cc43bf7974ce37363a4353027a3a056d634b239ff7ffedf343
+size: 36061962 bytes
+sha256: 5f03732f27f9ff4262949256035d8c4a6c60af5823e85a20bb7a33c763f72e3a

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

@@ -1524,8 +1524,11 @@ export const wasmextractionconfig_mimeDetectionPolicy: (a: number) => [number, n
 export const wasmextractionconfig_needsImageData: (a: number) => number;
 export const wasmextractionconfig_needsImageProcessing: (a: number) => number;
 export const wasmextractionconfig_ner: (a: number) => number;
-export const wasmextractionconfig_new: (a: number, b: number, c: number, d: number, e: number, f: number, g: number, h: number, i: number, j: number, k: number, l: number, m: number, n: number, o: number, p: number, q: number, r: number, s: number, t: number, u: number, v: number, w: number, x: number, y: number, z: number, a1: number, b1: number, c1: number, d1: number, e1: number, f1: bigint, g1: number, h1: number, i1: number, j1: bigint, k1: number, l1: number, m1: number, n1: number, o1: number, p1: number, q1: bigint, r1: number, s1: number, t1: number, u1: number, v1: number, w1: number, x1: number, y1: number, z1: number, a2: number, b2: number, c2: number, d2: number) => number;
+export const wasmextractionconfig_new: (a: number, b: number, c: number, d: number, e: number, f: number, g: number, h: number, i: number, j: number, k: number, l: number, m: number, n: number, o: number, p: number, q: number, r: number, s: number, t: number, u: number, v: number, w: number, x: number, y: number, z: number, a1: number, b1: number, c1: number, d1: number, e1: number, f1: number, g1: number, h1: number, i1: bigint, j1: number, k1: number, l1: number, m1: bigint, n1: number, o1: number, p1: number, q1: number, r1: number, s1: number, t1: bigint, u1: number, v1: number, w1: number, x1: number, y1: number, z1: number, a2: number, b2: number, c2: number, d2: number, e2: number, f2: number, g2: number) => number;
 export const wasmextractionconfig_ocr: (a: number) => number;
+export const wasmextractionconfig_ocrEmbeddedImages: (a: number) => number;
+export const wasmextractionconfig_ocrNearEmptyFallback: (a: number) => number;
+export const wasmextractionconfig_ocrScannedPageQualityGate: (a: number) => number;
 export const wasmextractionconfig_ocrStrategy: (a: number) => any;
 export const wasmextractionconfig_outputFormat: (a: number) => any;
 export const wasmextractionconfig_pageClassification: (a: number) => number;
@@ -1569,6 +1572,9 @@ export const wasmextractionconfig_set_maxEmbeddedFileBytes: (a: number, b: numbe
 export const wasmextractionconfig_set_mimeDetectionPolicy: (a: number, b: number) => void;
 export const wasmextractionconfig_set_ner: (a: number, b: number) => void;
 export const wasmextractionconfig_set_ocr: (a: number, b: number) => void;
+export const wasmextractionconfig_set_ocrEmbeddedImages: (a: number, b: number) => void;
+export const wasmextractionconfig_set_ocrNearEmptyFallback: (a: number, b: number) => void;
+export const wasmextractionconfig_set_ocrScannedPageQualityGate: (a: number, b: number) => void;
 export const wasmextractionconfig_set_ocrStrategy: (a: number, b: any) => void;
 export const wasmextractionconfig_set_outputFormat: (a: number, b: any) => void;
 export const wasmextractionconfig_set_pageClassification: (a: number, b: number) => void;