pdf-codec 5.5.1 → 5.6.1

package/dist/images-read.js

@@ -57,27 +57,51 @@ function resolveColorSpace(csObj, resolver, sink) {
 		name: family ?? "(unrecognised array colour space)"
 	};
 }
-function unpackSamples(data, width, height, componentsPerPixel, bitsPerComponent) {
-	if (bitsPerComponent === BITS_PER_BYTE) return Array.from(data.subarray(0, width * height * componentsPerPixel));
+/**
+* Allocates the buffers one `decodeImageSamples` call needs and counts their bytes, so a test can bound the decode's memory in bytes rather than time.
+*/
+var SampleDecodeWork = class {
+	#bytesAllocated = 0;
+	/** Bytes of every buffer the decode allocated: its raster, its one reusable row and its lookup table. Each lives until the decode returns, so this is also the decode's peak; a view onto the stream it was given costs nothing. */
+	get bytesAllocated() {
+		return this.#bytesAllocated;
+	}
+	/**
+	* A zero-filled buffer of `length` bytes, counted.
+	* @param length - Its length in bytes.
+	* @returns The buffer.
+	*/
+	allocate(length) {
+		this.#bytesAllocated += length;
+		return new Uint8Array(length);
+	}
+};
+function readSampleRow(data, row, bitsPerComponent, target) {
+	const samplesPerRow = target.length;
+	if (bitsPerComponent === BITS_PER_BYTE) {
+		const rowStart = row * samplesPerRow;
+		for (let s = 0; s < samplesPerRow; s++) target[s] = data[rowStart + s] ?? 0;
+		return;
+	}
+	const rowStart = row * Math.ceil(samplesPerRow * bitsPerComponent / BITS_PER_BYTE);
+	const sampleMask = (1 << bitsPerComponent) - 1;
+	for (let s = 0; s < samplesPerRow; s++) {
+		const bitPos = s * bitsPerComponent;
+		const byte = data[rowStart + Math.floor(bitPos / BITS_PER_BYTE)] ?? 0;
+		const shift = BITS_PER_BYTE - bitsPerComponent - bitPos % BITS_PER_BYTE;
+		target[s] = byte >> shift & sampleMask;
+	}
+}
+function forEachSampleRow(data, width, height, componentsPerPixel, bitsPerComponent, work, visit) {
 	const samplesPerRow = width * componentsPerPixel;
-	const bytesPerRow = Math.ceil(samplesPerRow * bitsPerComponent / BITS_PER_BYTE);
-	const out = [];
+	const rowSamples = work.allocate(samplesPerRow);
 	for (let row = 0; row < height; row++) {
-		const rowStart = row * bytesPerRow;
-		let bitPos = 0;
-		for (let s = 0; s < samplesPerRow; s++) {
-			let value = 0;
-			for (let b = 0; b < bitsPerComponent; b++) {
-				const byteIndex = rowStart + Math.floor(bitPos / BITS_PER_BYTE);
-				const bitIndex = 7 - bitPos % BITS_PER_BYTE;
-				const bit = (data[byteIndex] ?? 0) >> bitIndex & 1;
-				value = value << 1 | bit;
-				bitPos++;
-			}
-			out.push(value);
-		}
+		readSampleRow(data, row, bitsPerComponent, rowSamples);
+		visit(rowSamples, row * samplesPerRow);
 	}
-	return out;
+}
+function availableSampleCount(data, sampleCount, bitsPerComponent) {
+	return bitsPerComponent === BITS_PER_BYTE ? Math.min(data.length, sampleCount) : sampleCount;
 }
 function scaleToByte(value, maxValue, inverted) {
 	const v = inverted ? maxValue - value : value;
@@ -106,56 +130,89 @@ function sampleFromPalette(base, lookup, offset) {
 		b: lookup[offset + 2] ?? 0
 	};
 }
-function buildRawImage(data, width, height, bitsPerComponent, colorSpace, inverted) {
+function scaleTable(maxValue, inverted, work) {
+	const table = work.allocate(maxValue + 1);
+	for (let value = 0; value <= maxValue; value++) table[value] = scaleToByte(value, maxValue, inverted);
+	return table;
+}
+/**
+* Decodes an image's samples into the 8-bit raster `encodePng` takes, holding at most the raster itself, one row of samples and a lookup table of at most 256 entries beside the stream; nothing is allocated per sample.
+* @param data - The image's decoded stream: rows of `width` pixels padded to a whole byte, sub-byte samples packed most significant bit first.
+* @param width - Pixels per row.
+* @param height - Rows.
+* @param bitsPerComponent - 1, 2, 4 or 8.
+* @param colorSpace - The resolved colour space; never `unsupported`.
+* @param inverted - Whether `/Decode` is `[1 0]`, which a gray, RGB or CMYK sample is inverted by and an indexed one ignores.
+* @param work - Counts the bytes allocated; see SampleDecodeWork.
+* @returns A gray or RGB raster. An 8-bit gray or RGB image with no `/Decode` inversion is already that raster, so its data is a view onto `data` and costs no allocation. An 8-bit stream shorter than the image yields a gray, RGB or indexed raster holding only the pixels the stream covers, and a CMYK one in which each missing sample reads as 0.
+*/
+function decodeImageSamples(data, width, height, bitsPerComponent, colorSpace, inverted, work = new SampleDecodeWork()) {
 	const maxValue = (1 << bitsPerComponent) - 1;
+	const pixelCount = width * height;
 	if (colorSpace.kind === "indexed") {
-		const indices = unpackSamples(data, width, height, 1, bitsPerComponent);
+		const channels = colorSpace.base.kind === "gray" ? 1 : RGB_CHANNEL_COUNT;
 		const baseComponents = componentsOf(colorSpace.base);
-		const out = new Uint8Array(width * height * (colorSpace.base.kind === "gray" ? 1 : RGB_CHANNEL_COUNT));
-		let outIdx = 0;
-		for (const index of indices) {
+		const palette = work.allocate((maxValue + 1) * channels);
+		for (let index = 0; index <= maxValue; index++) {
 			const rgb = sampleFromPalette(colorSpace.base, colorSpace.lookup, index * baseComponents);
-			if (colorSpace.base.kind === "gray") out[outIdx++] = rgb.r;
-			else {
-				out[outIdx++] = rgb.r;
-				out[outIdx++] = rgb.g;
-				out[outIdx++] = rgb.b;
+			palette[index * channels] = rgb.r;
+			if (channels === RGB_CHANNEL_COUNT) {
+				palette[index * channels + 1] = rgb.g;
+				palette[index * channels + 2] = rgb.b;
 			}
 		}
+		const out = work.allocate(pixelCount * channels);
+		const indexed = availableSampleCount(data, pixelCount, bitsPerComponent);
+		forEachSampleRow(data, width, height, 1, bitsPerComponent, work, (indices, firstPixel) => {
+			const count = Math.min(indices.length, indexed - firstPixel);
+			for (let i = 0; i < count; i++) {
+				const entry = indices[i] * channels;
+				const at = (firstPixel + i) * channels;
+				for (let channel = 0; channel < channels; channel++) out[at + channel] = palette[entry + channel];
+			}
+		});
 		return {
 			width,
 			height,
-			channels: colorSpace.base.kind === "gray" ? 1 : RGB_CHANNEL_COUNT,
+			channels,
 			data: out
 		};
 	}
-	if (colorSpace.kind === "gray") {
-		const samples = unpackSamples(data, width, height, 1, bitsPerComponent);
-		return {
+	if (colorSpace.kind === "gray" || colorSpace.kind === "rgb") {
+		const channels = colorSpace.kind === "gray" ? 1 : RGB_CHANNEL_COUNT;
+		const available = availableSampleCount(data, pixelCount * channels, bitsPerComponent);
+		if (bitsPerComponent === BITS_PER_BYTE && !inverted) return {
 			width,
 			height,
-			channels: 1,
-			data: Uint8Array.from(samples, (v) => scaleToByte(v, maxValue, inverted))
+			channels,
+			data: data.subarray(0, available)
 		};
-	}
-	if (colorSpace.kind === "rgb") {
-		const samples = unpackSamples(data, width, height, RGB_CHANNEL_COUNT, bitsPerComponent);
-		const out = Uint8Array.from(samples, (v) => scaleToByte(v, maxValue, inverted));
+		const scale = scaleTable(maxValue, inverted, work);
+		const out = work.allocate(available);
+		forEachSampleRow(data, width, height, channels, bitsPerComponent, work, (samples, firstSample) => {
+			const count = Math.min(samples.length, available - firstSample);
+			for (let i = 0; i < count; i++) out[firstSample + i] = scale[samples[i]];
+		});
 		return {
 			width,
 			height,
-			channels: RGB_CHANNEL_COUNT,
+			channels,
 			data: out
 		};
 	}
-	const samples = unpackSamples(data, width, height, CMYK_COMPONENT_COUNT, bitsPerComponent);
-	const out = new Uint8Array(width * height * RGB_CHANNEL_COUNT);
-	for (let px = 0; px < width * height; px++) {
-		const rgb = cmykToRgbByte(scaleToByte(samples[px * CMYK_COMPONENT_COUNT] ?? 0, maxValue, inverted) / MAX_BYTE_VALUE, scaleToByte(samples[px * CMYK_COMPONENT_COUNT + 1] ?? 0, maxValue, inverted) / MAX_BYTE_VALUE, scaleToByte(samples[px * CMYK_COMPONENT_COUNT + 2] ?? 0, maxValue, inverted) / MAX_BYTE_VALUE, scaleToByte(samples[px * CMYK_COMPONENT_COUNT + 3] ?? 0, maxValue, inverted) / MAX_BYTE_VALUE);
-		out[px * RGB_CHANNEL_COUNT] = rgb.r;
-		out[px * RGB_CHANNEL_COUNT + 1] = rgb.g;
-		out[px * RGB_CHANNEL_COUNT + 2] = rgb.b;
-	}
+	const scale = scaleTable(maxValue, inverted, work);
+	const out = work.allocate(pixelCount * RGB_CHANNEL_COUNT);
+	forEachSampleRow(data, width, height, CMYK_COMPONENT_COUNT, bitsPerComponent, work, (samples, firstSample) => {
+		const firstPixel = firstSample / CMYK_COMPONENT_COUNT;
+		for (let px = 0; px < width; px++) {
+			const base = px * CMYK_COMPONENT_COUNT;
+			const rgb = cmykToRgbByte(scale[samples[base]] / MAX_BYTE_VALUE, scale[samples[base + 1]] / MAX_BYTE_VALUE, scale[samples[base + 2]] / MAX_BYTE_VALUE, scale[samples[base + 3]] / MAX_BYTE_VALUE);
+			const outBase = (firstPixel + px) * RGB_CHANNEL_COUNT;
+			out[outBase] = rgb.r;
+			out[outBase + 1] = rgb.g;
+			out[outBase + 2] = rgb.b;
+		}
+	});
 	return {
 		width,
 		height,
@@ -326,7 +383,7 @@ function readImageXObject(dict, raw, resolver, sink) {
 	}
 	const decodeArr = asArray(dictGet(dict, "Decode"));
 	const inverted = decodeArr !== void 0 && asNumber(decodeArr[0]) === 1 && asNumber(decodeArr[1]) === 0;
-	const rawImage = buildRawImage(decoded.bytes, width, height, bitsPerComponent, colorSpace, inverted);
+	const rawImage = decodeImageSamples(decoded.bytes, width, height, bitsPerComponent, colorSpace, inverted);
 	const alpha = readSoftMaskAlpha(dict, width, height, resolver, sink);
 	const withAlpha = alpha !== void 0 ? {
 		...rawImage,
@@ -341,4 +398,4 @@ function readImageXObject(dict, raw, resolver, sink) {
 	};
 }
 //#endregion
-export { cmykToRgbByte, readImageXObject, sampleFromPalette, scaleToByte };
+export { SampleDecodeWork, cmykToRgbByte, decodeImageSamples, readImageXObject, sampleFromPalette, scaleToByte };

package/dist/index.cjs

@@ -21,7 +21,7 @@ const require_write_skipped_surfaces = require("./write-skipped-surfaces.cjs");
 const require_write = require("./write.cjs");
 const require_codec = require("./codec.cjs");
 const require_font_face = require("./font-face.cjs");
-const require_raster = require("./raster-HUE5bw5s.cjs");
+const require_raster = require("./raster-B8i3Tgjj.cjs");
 exports.DEFAULT_BASELINE_TOLERANCE_EM = require_text_group.DEFAULT_BASELINE_TOLERANCE_EM;
 exports.DEFAULT_COLUMN_GAP_EM = require_text_group.DEFAULT_COLUMN_GAP_EM;
 exports.DEFAULT_VERTICAL_METRIC_POLICY = require_measure.DEFAULT_VERTICAL_METRIC_POLICY;

package/dist/index.js

@@ -20,6 +20,6 @@ import { PdfSkippedSurfacesError } from "./write-skipped-surfaces.js";
 import { PdfPartialDocumentError, writePdf } from "./write.js";
 import { PdfBytesSchema, pdfCodec } from "./codec.js";
 import { FontFaceParseError, readFontFace } from "./font-face.js";
-import { r as renderPdfPage } from "./raster-DUmwfi3F.js";
+import { r as renderPdfPage } from "./raster-CIc6ot36.js";
 export * from "byte-codec";
 export { DEFAULT_BASELINE_TOLERANCE_EM, DEFAULT_COLUMN_GAP_EM, DEFAULT_VERTICAL_METRIC_POLICY, DEFAULT_WORD_GAP_EM, FontFaceParseError, Jbig2ParseError, Jbig2UnsupportedError, Jpeg2000ParseError, Jpeg2000UnsupportedError, LAYOUT_FORMAT_VERSION, LayoutAnnotationQuadSchema, LayoutAnnotationSchema, LayoutAttachmentSchema, LayoutDestinationSchema, LayoutDestinationTargetSchema, LayoutDocumentSchema, LayoutDocumentSurfaceSchema, LayoutEllipseSchema, LayoutFormFieldSchema, LayoutFormWidgetSchema, LayoutImageAssetSchema, LayoutImageSchema, LayoutInternalLinkSchema, LayoutItemSchema, LayoutLayerSchema, LayoutLineSchema, LayoutLinkSchema, LayoutOutlineItemSchema, LayoutPageSchema, LayoutPathSchema, LayoutPathSegmentSchema, LayoutRectSchema, LayoutStructureElementSchema, LayoutSubpathSchema, LayoutTextSchema, NOOP_DIAGNOSTIC_SINK, PdfBytesSchema, PdfEncryptedError, PdfEncryptionError, PdfPageSelectionError, PdfParseError, PdfPartialDocumentError, PdfPasswordRequiredError, PdfSkippedSurfacesError, STANDARD_METRICS, assembleStretchyGlyph, createFontMeasurer, createFontRegistry, createStandardFontMeasurer, decodeCcittFax, decodeJbig2Embedded, decodeJpeg2000, filterScanlines, groupPdfTextRuns, loadMathFont, looksLikeBareCodestream, parseJp2Container, pdfCodec, readFontFace, readJpeg2000Metadata, readPdf, renderPdfPage, resolveFaceWithRegistry, resolveStandardFont, runGapPt, runsShareBaseline, scaleMathStretchConstruction, sourcePageIndex, unfilterScanlines, writePdf };

package/dist/{interpret-BDVrFWhd.cjs → interpret-2_N_lh0h.cjs}

@@ -306,10 +306,9 @@ function runContentStream(bytes, resources, initialState, context, depth, marked
 			advanceThroughString(el.bytes);
 		} else if (el.kind === "number") {
 			const adjustment = -(el.value / GLYPH_SPACE_PER_TEXT_SPACE_UNIT) * gs.fontSizePt;
-			const endsRun = !vertical && totalLength > 0 && adjustment >= .125 * gs.fontSizePt;
-			if (endsRun) flushRun();
+			if (!vertical && totalLength > 0 && adjustment >= .125 * gs.fontSizePt) flushRun();
 			text.tm = require_matrix.multiplyMatrices(vertical ? require_matrix.translationMatrix(0, adjustment) : require_matrix.translationMatrix(adjustment * gs.horizScale, 0), text.tm);
-			if (endsRun) startMatrix = computeTrm(gs, text);
+			if (totalLength === 0) startMatrix = computeTrm(gs, text);
 		}
 		flushRun();
 	};

package/dist/{interpret---0lZPlv.js → interpret-BeMKZGBm.js}

@@ -306,10 +306,9 @@ function runContentStream(bytes, resources, initialState, context, depth, marked
 			advanceThroughString(el.bytes);
 		} else if (el.kind === "number") {
 			const adjustment = -(el.value / GLYPH_SPACE_PER_TEXT_SPACE_UNIT) * gs.fontSizePt;
-			const endsRun = !vertical && totalLength > 0 && adjustment >= .125 * gs.fontSizePt;
-			if (endsRun) flushRun();
+			if (!vertical && totalLength > 0 && adjustment >= .125 * gs.fontSizePt) flushRun();
 			text.tm = multiplyMatrices(vertical ? translationMatrix(0, adjustment) : translationMatrix(adjustment * gs.horizScale, 0), text.tm);
-			if (endsRun) startMatrix = computeTrm(gs, text);
+			if (totalLength === 0) startMatrix = computeTrm(gs, text);
 		}
 		flushRun();
 	};

package/dist/interpret-colors.cjs

@@ -1,5 +1,5 @@
 Object.defineProperty(exports, Symbol.toStringTag, { value: "Module" });
-const require_interpret = require("./interpret-BDVrFWhd.cjs");
+const require_interpret = require("./interpret-2_N_lh0h.cjs");
 exports.cmykColor = require_interpret.cmykColor;
 exports.genericColor = require_interpret.genericColor;
 exports.grayColor = require_interpret.grayColor;

package/dist/interpret-colors.js

@@ -1,2 +1,2 @@
-import { a as grayColor, i as genericColor, o as rgbColor, r as cmykColor } from "./interpret---0lZPlv.js";
+import { a as grayColor, i as genericColor, o as rgbColor, r as cmykColor } from "./interpret-BeMKZGBm.js";
 export { cmykColor, genericColor, grayColor, rgbColor };

package/dist/interpret.cjs

@@ -1,4 +1,4 @@
 Object.defineProperty(exports, Symbol.toStringTag, { value: "Module" });
-const require_interpret = require("./interpret-BDVrFWhd.cjs");
+const require_interpret = require("./interpret-2_N_lh0h.cjs");
 exports.interpretContentStream = require_interpret.interpretContentStream;
 exports.numAt = require_interpret.numAt;

package/dist/interpret.js

@@ -1,2 +1,2 @@
-import { n as numAt, t as interpretContentStream } from "./interpret---0lZPlv.js";
+import { n as numAt, t as interpretContentStream } from "./interpret-BeMKZGBm.js";
 export { interpretContentStream, numAt };

package/dist/layout.cjs

@@ -270,7 +270,7 @@ const LayoutStructureElementSchema = zod.z.lazy(() => zod.z.object({
 	children: zod.z.array(LayoutStructureElementSchema)
 }));
 /**
-* The document-level surfaces a read can leave out (`ReadPdfOptions.surfaces`), each named by the `LayoutDocument` field it fills: `outline`, `destinations`, `form`, `layers` and `structure` are those fields, and `residue` is the package-level `source` channel. A `LayoutDocument` lists the ones its read skipped in `skippedSurfaces`.
+* The document-level surfaces a read can leave out (`ReadPdfOptions.surfaces`), each named by the `LayoutDocument` field it fills: `outline`, `destinations`, `form`, `layers`, `structure` and `images` are those fields, and `residue` is the package-level `source` channel. A `LayoutDocument` lists the ones its read skipped in `skippedSurfaces`.
 */
 const LayoutDocumentSurfaceSchema = zod.z.enum([
 	"outline",
@@ -278,7 +278,8 @@ const LayoutDocumentSurfaceSchema = zod.z.enum([
 	"form",
 	"layers",
 	"structure",
-	"residue"
+	"residue",
+	"images"
 ]);
 const LayoutDocumentSchema = zod.z.object({
 	formatVersion: zod.z.literal(1),

package/dist/layout.d.cts

@@ -785,10 +785,11 @@ interface LayoutStructureElement {
   readonly children: readonly LayoutStructureElement[];
 }
 /**
- * The document-level surfaces a read can leave out (`ReadPdfOptions.surfaces`), each named by the `LayoutDocument` field it fills: `outline`, `destinations`, `form`, `layers` and `structure` are those fields, and `residue` is the package-level `source` channel. A `LayoutDocument` lists the ones its read skipped in `skippedSurfaces`.
+ * The document-level surfaces a read can leave out (`ReadPdfOptions.surfaces`), each named by the `LayoutDocument` field it fills: `outline`, `destinations`, `form`, `layers`, `structure` and `images` are those fields, and `residue` is the package-level `source` channel. A `LayoutDocument` lists the ones its read skipped in `skippedSurfaces`.
  */
 declare const LayoutDocumentSurfaceSchema: z.ZodEnum<{
   structure: "structure";
+  images: "images";
   destinations: "destinations";
   outline: "outline";
   layers: "layers";
@@ -1115,6 +1116,7 @@ declare const LayoutDocumentSchema: z.ZodObject<{
   }, z.core.$strict>>>;
   skippedSurfaces: z.ZodOptional<z.ZodArray<z.ZodEnum<{
     structure: "structure";
+    images: "images";
     destinations: "destinations";
     outline: "outline";
     layers: "layers";

package/dist/layout.d.ts

@@ -785,10 +785,11 @@ interface LayoutStructureElement {
   readonly children: readonly LayoutStructureElement[];
 }
 /**
- * The document-level surfaces a read can leave out (`ReadPdfOptions.surfaces`), each named by the `LayoutDocument` field it fills: `outline`, `destinations`, `form`, `layers` and `structure` are those fields, and `residue` is the package-level `source` channel. A `LayoutDocument` lists the ones its read skipped in `skippedSurfaces`.
+ * The document-level surfaces a read can leave out (`ReadPdfOptions.surfaces`), each named by the `LayoutDocument` field it fills: `outline`, `destinations`, `form`, `layers`, `structure` and `images` are those fields, and `residue` is the package-level `source` channel. A `LayoutDocument` lists the ones its read skipped in `skippedSurfaces`.
  */
 declare const LayoutDocumentSurfaceSchema: z.ZodEnum<{
   structure: "structure";
+  images: "images";
   destinations: "destinations";
   outline: "outline";
   layers: "layers";
@@ -1115,6 +1116,7 @@ declare const LayoutDocumentSchema: z.ZodObject<{
   }, z.core.$strict>>>;
   skippedSurfaces: z.ZodOptional<z.ZodArray<z.ZodEnum<{
     structure: "structure";
+    images: "images";
     destinations: "destinations";
     outline: "outline";
     layers: "layers";

package/dist/layout.js

@@ -269,7 +269,7 @@ const LayoutStructureElementSchema = z.lazy(() => z.object({
 	children: z.array(LayoutStructureElementSchema)
 }));
 /**
-* The document-level surfaces a read can leave out (`ReadPdfOptions.surfaces`), each named by the `LayoutDocument` field it fills: `outline`, `destinations`, `form`, `layers` and `structure` are those fields, and `residue` is the package-level `source` channel. A `LayoutDocument` lists the ones its read skipped in `skippedSurfaces`.
+* The document-level surfaces a read can leave out (`ReadPdfOptions.surfaces`), each named by the `LayoutDocument` field it fills: `outline`, `destinations`, `form`, `layers`, `structure` and `images` are those fields, and `residue` is the package-level `source` channel. A `LayoutDocument` lists the ones its read skipped in `skippedSurfaces`.
 */
 const LayoutDocumentSurfaceSchema = z.enum([
 	"outline",
@@ -277,7 +277,8 @@ const LayoutDocumentSurfaceSchema = z.enum([
 	"form",
 	"layers",
 	"structure",
-	"residue"
+	"residue",
+	"images"
 ]);
 const LayoutDocumentSchema = z.object({
 	formatVersion: z.literal(1),

package/dist/{raster-HUE5bw5s.cjs → raster-B8i3Tgjj.cjs}

@@ -11,7 +11,7 @@ const require_diagnostics = require("./diagnostics.cjs");
 const require_document = require("./document.cjs");
 const require_util_abort = require("./util/abort.cjs");
 const require_font_read = require("./font-read.cjs");
-const require_interpret = require("./interpret-BDVrFWhd.cjs");
+const require_interpret = require("./interpret-2_N_lh0h.cjs");
 const require_read = require("./read.cjs");
 const require_glyf = require("./glyf.cjs");
 const require_glyf_contours = require("./glyf-contours.cjs");

package/dist/{raster-DUmwfi3F.js → raster-CIc6ot36.js}

@@ -11,7 +11,7 @@ import { NOOP_DIAGNOSTIC_SINK, PdfParseError } from "./diagnostics.js";
 import { openPdfDocument } from "./document.js";
 import { throwIfAborted } from "./util/abort.js";
 import { createFontResolver } from "./font-read.js";
-import { t as interpretContentStream } from "./interpret---0lZPlv.js";
+import { t as interpretContentStream } from "./interpret-BeMKZGBm.js";
 import { normalizeRotation, pageRotationTransform } from "./read.js";
 import { parseGlyf } from "./glyf.js";
 import { decodeGlyphOutline } from "./glyf-contours.js";

package/dist/raster-text.cjs

@@ -1,5 +1,5 @@
 Object.defineProperty(exports, Symbol.toStringTag, { value: "Module" });
-const require_raster = require("./raster-HUE5bw5s.cjs");
+const require_raster = require("./raster-B8i3Tgjj.cjs");
 exports.drawGlyphOutline = require_raster.drawGlyphOutline;
 exports.drawTextRun = require_raster.drawTextRun;
 exports.glyphOutlineSubpaths = require_raster.glyphOutlineSubpaths;

package/dist/raster-text.js

@@ -1,2 +1,2 @@
-import { a as drawTextRun, i as drawGlyphOutline, o as glyphOutlineSubpaths } from "./raster-DUmwfi3F.js";
+import { a as drawTextRun, i as drawGlyphOutline, o as glyphOutlineSubpaths } from "./raster-CIc6ot36.js";
 export { drawGlyphOutline, drawTextRun, glyphOutlineSubpaths };

package/dist/raster.cjs

@@ -1,5 +1,5 @@
 Object.defineProperty(exports, Symbol.toStringTag, { value: "Module" });
-const require_raster = require("./raster-HUE5bw5s.cjs");
+const require_raster = require("./raster-B8i3Tgjj.cjs");
 exports.EXTENT_ZERO_EPSILON = require_raster.EXTENT_ZERO_EPSILON;
 exports.flattenCubic = require_raster.flattenCubic;
 exports.renderPdfPage = require_raster.renderPdfPage;

package/dist/raster.js

@@ -1,2 +1,2 @@
-import { n as flattenCubic, r as renderPdfPage, t as EXTENT_ZERO_EPSILON } from "./raster-DUmwfi3F.js";
+import { n as flattenCubic, r as renderPdfPage, t as EXTENT_ZERO_EPSILON } from "./raster-CIc6ot36.js";
 export { EXTENT_ZERO_EPSILON, flattenCubic, renderPdfPage };

package/dist/read-convert.cjs

@@ -7,14 +7,25 @@ const require_bytes_crc32 = require("./bytes/crc32.cjs");
 const require_images_read = require("./images-read.cjs");
 let byte_codec = require("byte-codec");
 //#region src/read-convert.ts
-function convertExtractedItem(item, pageMatrix, fontResolver, images, imageIdCache, resolver, sink) {
+/**
+* Converts one interpreted item to a layout item in page space.
+* @param item - The item the content-stream interpreter extracted.
+* @param pageMatrix - Maps the interpreter's user space into the page's output space.
+* @param fontResolver - Resolves a text item's font.
+* @param imageRegistry - Where images are decoded into, or undefined for a read that skips images, which converts no image item and decodes no image stream.
+* @param resolver - Resolves indirect objects an image names.
+* @param sink - Receives diagnostics.
+* @returns The layout item, or undefined for an item that converts to none: an image that could not be decoded, or any image when `imageRegistry` is undefined.
+*/
+function convertExtractedItem(item, pageMatrix, fontResolver, imageRegistry, resolver, sink) {
 	if (item.kind === "text") return convertText(item, pageMatrix, fontResolver);
 	if (item.kind === "rect") return convertRect(item, pageMatrix);
 	if (item.kind === "ellipse") return convertEllipse(item, pageMatrix);
 	if (item.kind === "line") return convertLine(item, pageMatrix);
 	if (item.kind === "path") return convertPath(item, pageMatrix);
-	if (item.kind === "image") return convertImage(item, pageMatrix, images, imageIdCache, resolver, sink);
-	return convertInlineImage(item, pageMatrix, images, resolver, sink);
+	if (imageRegistry === void 0) return;
+	if (item.kind === "image") return convertImage(item, pageMatrix, imageRegistry.images, imageRegistry.imageIdCache, resolver, sink);
+	return convertInlineImage(item, pageMatrix, imageRegistry.images, resolver, sink);
 }
 function convertText(item, pageMatrix, fontResolver) {
 	const font = fontResolver.resolve(item.fontResourceName, item.resources);

package/dist/read-convert.d.cts

@@ -8,7 +8,24 @@ import { DestinationRegistry } from "./navigation.cjs";
 import { ExtractedPdfImage } from "./images-read.cjs";
 import { Color } from "document-schema.js";
 //#region src/read-convert.d.ts
-declare function convertExtractedItem(item: ExtractedItem, pageMatrix: Matrix, fontResolver: FontResolverService, images: Record<string, LayoutImageAsset>, imageIdCache: Map<PdfDict, string | null>, resolver: Readonly<PdfObjectResolver>, sink: PdfDiagnosticSink): LayoutItem | undefined;
+/**
+ * Where a read's images go: the registry each decoded image is stored in once, and the id each image XObject dictionary already decoded to (null for one that could not be).
+ */
+interface ImageRegistry {
+  readonly images: Record<string, LayoutImageAsset>;
+  readonly imageIdCache: Map<PdfDict, string | null>;
+}
+/**
+ * Converts one interpreted item to a layout item in page space.
+ * @param item - The item the content-stream interpreter extracted.
+ * @param pageMatrix - Maps the interpreter's user space into the page's output space.
+ * @param fontResolver - Resolves a text item's font.
+ * @param imageRegistry - Where images are decoded into, or undefined for a read that skips images, which converts no image item and decodes no image stream.
+ * @param resolver - Resolves indirect objects an image names.
+ * @param sink - Receives diagnostics.
+ * @returns The layout item, or undefined for an item that converts to none: an image that could not be decoded, or any image when `imageRegistry` is undefined.
+ */
+declare function convertExtractedItem(item: ExtractedItem, pageMatrix: Matrix, fontResolver: FontResolverService, imageRegistry: ImageRegistry | undefined, resolver: Readonly<PdfObjectResolver>, sink: PdfDiagnosticSink): LayoutItem | undefined;
 declare function convertText(item: ExtractedTextRun, pageMatrix: Matrix, fontResolver: FontResolverService): LayoutText | undefined;
 declare function paintFields(paint: ExtractedPaint): {
   fill?: Color;
@@ -55,4 +72,4 @@ declare function convertImage(item: ExtractedImage, pageMatrix: Matrix, images:
 declare function readLinkAnnotations(page: PdfDict, pageMatrix: Matrix, resolver: Readonly<PdfObjectResolver>, destinationRegistry: DestinationRegistry): (LayoutLink | LayoutInternalLink)[];
 declare function readPageNotes(page: PdfDict, resolver: Readonly<PdfObjectResolver>): string | undefined;
 //#endregion
-export { convertEllipse, convertExtractedItem, convertImage, convertLine, convertPath, convertRect, convertText, imagePlacementFrom, paintFields, readLinkAnnotations, readPageNotes, registerExtractedImage, resolveCachedImageId, transformBox, transformSubpath };
+export { ImageRegistry, convertEllipse, convertExtractedItem, convertImage, convertLine, convertPath, convertRect, convertText, imagePlacementFrom, paintFields, readLinkAnnotations, readPageNotes, registerExtractedImage, resolveCachedImageId, transformBox, transformSubpath };

package/dist/read-convert.d.ts

@@ -8,7 +8,24 @@ import { DestinationRegistry } from "./navigation.js";
 import { ExtractedPdfImage } from "./images-read.js";
 import { Color } from "document-schema.js";
 //#region src/read-convert.d.ts
-declare function convertExtractedItem(item: ExtractedItem, pageMatrix: Matrix, fontResolver: FontResolverService, images: Record<string, LayoutImageAsset>, imageIdCache: Map<PdfDict, string | null>, resolver: Readonly<PdfObjectResolver>, sink: PdfDiagnosticSink): LayoutItem | undefined;
+/**
+ * Where a read's images go: the registry each decoded image is stored in once, and the id each image XObject dictionary already decoded to (null for one that could not be).
+ */
+interface ImageRegistry {
+  readonly images: Record<string, LayoutImageAsset>;
+  readonly imageIdCache: Map<PdfDict, string | null>;
+}
+/**
+ * Converts one interpreted item to a layout item in page space.
+ * @param item - The item the content-stream interpreter extracted.
+ * @param pageMatrix - Maps the interpreter's user space into the page's output space.
+ * @param fontResolver - Resolves a text item's font.
+ * @param imageRegistry - Where images are decoded into, or undefined for a read that skips images, which converts no image item and decodes no image stream.
+ * @param resolver - Resolves indirect objects an image names.
+ * @param sink - Receives diagnostics.
+ * @returns The layout item, or undefined for an item that converts to none: an image that could not be decoded, or any image when `imageRegistry` is undefined.
+ */
+declare function convertExtractedItem(item: ExtractedItem, pageMatrix: Matrix, fontResolver: FontResolverService, imageRegistry: ImageRegistry | undefined, resolver: Readonly<PdfObjectResolver>, sink: PdfDiagnosticSink): LayoutItem | undefined;
 declare function convertText(item: ExtractedTextRun, pageMatrix: Matrix, fontResolver: FontResolverService): LayoutText | undefined;
 declare function paintFields(paint: ExtractedPaint): {
   fill?: Color;
@@ -55,4 +72,4 @@ declare function convertImage(item: ExtractedImage, pageMatrix: Matrix, images:
 declare function readLinkAnnotations(page: PdfDict, pageMatrix: Matrix, resolver: Readonly<PdfObjectResolver>, destinationRegistry: DestinationRegistry): (LayoutLink | LayoutInternalLink)[];
 declare function readPageNotes(page: PdfDict, resolver: Readonly<PdfObjectResolver>): string | undefined;
 //#endregion
-export { convertEllipse, convertExtractedItem, convertImage, convertLine, convertPath, convertRect, convertText, imagePlacementFrom, paintFields, readLinkAnnotations, readPageNotes, registerExtractedImage, resolveCachedImageId, transformBox, transformSubpath };
+export { ImageRegistry, convertEllipse, convertExtractedItem, convertImage, convertLine, convertPath, convertRect, convertText, imagePlacementFrom, paintFields, readLinkAnnotations, readPageNotes, registerExtractedImage, resolveCachedImageId, transformBox, transformSubpath };

package/dist/read-convert.js

@@ -6,14 +6,25 @@ import { crc32 } from "./bytes/crc32.js";
 import { readImageXObject } from "./images-read.js";
 import { bytesToBase64 } from "byte-codec";
 //#region src/read-convert.ts
-function convertExtractedItem(item, pageMatrix, fontResolver, images, imageIdCache, resolver, sink) {
+/**
+* Converts one interpreted item to a layout item in page space.
+* @param item - The item the content-stream interpreter extracted.
+* @param pageMatrix - Maps the interpreter's user space into the page's output space.
+* @param fontResolver - Resolves a text item's font.
+* @param imageRegistry - Where images are decoded into, or undefined for a read that skips images, which converts no image item and decodes no image stream.
+* @param resolver - Resolves indirect objects an image names.
+* @param sink - Receives diagnostics.
+* @returns The layout item, or undefined for an item that converts to none: an image that could not be decoded, or any image when `imageRegistry` is undefined.
+*/
+function convertExtractedItem(item, pageMatrix, fontResolver, imageRegistry, resolver, sink) {
 	if (item.kind === "text") return convertText(item, pageMatrix, fontResolver);
 	if (item.kind === "rect") return convertRect(item, pageMatrix);
 	if (item.kind === "ellipse") return convertEllipse(item, pageMatrix);
 	if (item.kind === "line") return convertLine(item, pageMatrix);
 	if (item.kind === "path") return convertPath(item, pageMatrix);
-	if (item.kind === "image") return convertImage(item, pageMatrix, images, imageIdCache, resolver, sink);
-	return convertInlineImage(item, pageMatrix, images, resolver, sink);
+	if (imageRegistry === void 0) return;
+	if (item.kind === "image") return convertImage(item, pageMatrix, imageRegistry.images, imageRegistry.imageIdCache, resolver, sink);
+	return convertInlineImage(item, pageMatrix, imageRegistry.images, resolver, sink);
 }
 function convertText(item, pageMatrix, fontResolver) {
 	const font = fontResolver.resolve(item.fontResourceName, item.resources);

package/dist/read.cjs

@@ -17,7 +17,7 @@ const require_diagnostics = require("./diagnostics.cjs");
 const require_document = require("./document.cjs");
 const require_util_abort = require("./util/abort.cjs");
 const require_font_read = require("./font-read.cjs");
-const require_interpret = require("./interpret-BDVrFWhd.cjs");
+const require_interpret = require("./interpret-2_N_lh0h.cjs");
 const require_navigation = require("./navigation.cjs");
 //#region src/read.ts
 function skippedSurfacesOf(surfaces) {
@@ -59,11 +59,14 @@ function readPdf(bytes, options) {
 		sink
 	});
 	const images = {};
-	const imageIdCache = /* @__PURE__ */ new Map();
 	const pageDicts = doc.pages();
 	const selection = options?.pages === void 0 ? void 0 : resolvePageSelection(options.pages, pageDicts.length);
 	const skippedSurfaces = skippedSurfacesOf(options?.surfaces);
 	const reads = (surface) => !skippedSurfaces.includes(surface);
+	const imageRegistry = reads("images") ? {
+		images,
+		imageIdCache: /* @__PURE__ */ new Map()
+	} : void 0;
 	const destinationRegistry = reads("destinations") ? require_navigation.createDestinationRegistry(doc.catalog, doc, (obj) => doc.pageIndex(obj), sink) : UNREAD_DESTINATION_REGISTRY;
 	const outline = reads("outline") ? require_navigation.readOutline(doc.catalog, destinationRegistry, doc, sink) : void 0;
 	const attachments = selection === void 0 ? require_attachments.readAttachments(doc.catalog, pageDicts, doc, sink) : [];
@@ -75,7 +78,7 @@ function readPdf(bytes, options) {
 	const pages = pageDicts.flatMap((pageDict, index) => {
 		if (selection !== void 0 && !selection.has(index)) return [];
 		require_util_abort.throwIfAborted(signal);
-		const read = readPage(index, pageDict, doc, fontResolver, images, imageIdCache, destinationRegistry, optionalContent?.layerNameOf ?? noLayerName, structure?.ownerOf ?? noStructureOwner, sink);
+		const read = readPage(index, pageDict, doc, fontResolver, imageRegistry, destinationRegistry, optionalContent?.layerNameOf ?? noLayerName, structure?.ownerOf ?? noStructureOwner, sink);
 		if (read.boxRow !== void 0) pageBoxRows.push(read.boxRow);
 		return [selection === void 0 ? read.page : {
 			...read.page,
@@ -309,7 +312,7 @@ function pageBoxResidueEntry(pageIndex, page, mediaBox, cropBox) {
 	for (const [key, value] of declaredBoxes) if (value !== void 0) entries[key] = value;
 	return require_objects.pdfDict(entries);
 }
-function readPage(pageIndex, page, resolver, fontResolver, images, imageIdCache, destinationRegistry, layerNameOf, structureOwnerOf, sink) {
+function readPage(pageIndex, page, resolver, fontResolver, imageRegistry, destinationRegistry, layerNameOf, structureOwnerOf, sink) {
 	const resources = resolver.resolveDict(require_objects.dictGet(page, "Resources"));
 	const mediaBox = readMediaBox(page);
 	let cropBox = readDeclaredPageBox(page, "CropBox") ?? mediaBox;
@@ -338,7 +341,7 @@ function readPage(pageIndex, page, resolver, fontResolver, images, imageIdCache,
 			layerNameOf
 		});
 		for (const item of extracted) {
-			const converted = require_read_convert.convertExtractedItem(item, pageMatrix, fontResolver, images, imageIdCache, resolver, sink);
+			const converted = require_read_convert.convertExtractedItem(item, pageMatrix, fontResolver, imageRegistry, resolver, sink);
 			if (converted === void 0 || !itemIntersectsVisibleRegion(converted, widthPt, heightPt)) continue;
 			const owner = item.mcid === void 0 ? void 0 : structureOwnerOf(pageIndex, item.mcid);
 			items.push(owner === void 0 ? converted : withStructure(converted, owner));

package/dist/read.d.cts

@@ -18,7 +18,7 @@ interface ReadPdfOptions {
   /**
    * Which document-level surfaces to read. Each is read unless its entry is `false`, so omitting the setting, or an entry, reads it as before. Independent of `pages`: it applies to a full read and a page-selected read alike.
    *
-   * A surface turned off is never parsed (its part of the catalog is not walked, so a malformed outline, form, layer list or structure tree reports no diagnostic) and its field is absent from the result whatever the file holds; the result lists it in `skippedSurfaces`, which is how a caller tells "not read" from "none". What each one covers, and what page items lose without it:
+   * A surface turned off is never parsed (its part of the catalog is not walked, so a malformed outline, form, layer list or structure tree reports no diagnostic, and no image a page draws is decoded or diagnosed) and its field is absent from the result whatever the file holds (`images` is left empty instead); the result lists it in `skippedSurfaces`, which is how a caller tells "not read" from "none". What each one covers, and what page items lose without it:
    *
    * - `outline`: the `/Outlines` bookmark tree (`outline`). Page items do not depend on it, except through minted names: a destination stated as a direct array is named with the first unused `destN` in the order the reader meets it, and the outline is read before any page, so an outline entry's direct destination takes a lower number than any link's. Without the outline, the names minted for page links' direct destinations are renumbered, and `destinations` loses the entries only the outline minted; each link still resolves to the same target.
    * - `destinations`: the named destinations of the catalog `/Dests` dictionary and the `/Names /Dests` name tree, and the registry links and outline entries name their targets through (`destinations`). Without it nothing can name an internal target, so a link whose target is internal (a `/Dest`, or a `/GoTo` action, named or direct) is left out of its page's items, and a read outline entry carries no `destination`; a link to a URI is kept as usual.
@@ -26,6 +26,7 @@ interface ReadPdfOptions {
    * - `layers`: optional content, the `/OCProperties` groups and their default visibility (`layers`). Without it no item carries a `layer`, since an `/OC` membership resolves to no name; the items themselves are all still read, so content the default view hides is indistinguishable from visible content.
    * - `structure`: the `/StructTreeRoot` element tree and its `/ParentTree` ownership map (`structure`). Without it no item carries a `structure` owner, and the parent-tree diagnostics are not reported.
    * - `residue`: the package-level residue rows (`source`), including the per-page `page-boxes` row. Page items do not depend on it; `metadata` still reads the XMP packet it falls back to.
+   * - `images`: the image registry (`images`), which holds every image XObject and inline image a read page draws, decoded to PNG or passed through as JPEG. Without it no image's stream is decoded, `images` is an empty record (every `LayoutDocument` carries one), and each page's `image` items are left out, since they would name assets that were never read. Decoding an image costs memory in proportion to its pixels, so a read that wants only a page's text leaves this out.
    *
    * Apart from those stated losses and the renumbering a skipped outline causes, every page item is exactly what a read with the surface on produces.
    */