js.documents 14.4.123 → 14.5.0

package/dist/markdown/write.cjs

@@ -6,6 +6,56 @@ const MATH_BLOCK_STYLE_ID = "MathBlock";
 const MATH_INLINE_FONT_MARKER = "Cambria Math";
 const MATH_INLINE_SOURCE = "markdown:math-inline";
 const PAGE_BREAK_MARKER = "<!-- page break -->";
+/**
+* The marker opening a page that `BuildMarkdownTextOptions.pageNumbers` labels: an HTML comment naming the page's number, `<!-- page 7 -->` for page 7, on a line of its own. An output-only annotation for readers of the text rather than a directive: unlike {@link PAGE_BREAK_MARKER} it states which page follows, not that a page ends, and nothing reads it back as one. Reading markdown that carries it keeps it as an ordinary HTML-comment paragraph, exactly as any other comment in a markdown source is kept, so a hand-written comment of the same shape is never mistaken for a label and lost.
+* @param pageNumber - the number the page is labelled with, as the caller supplied it
+* @returns the marker text
+*/
+function pageNumberMarker(pageNumber) {
+	return `<!-- page ${String(pageNumber)} -->`;
+}
+/**
+* `BuildMarkdownTextOptions.pageNumbers` did not supply exactly one number per page of the document. Thrown rather than labelling a prefix or padding, since a label on the wrong page is worse than none.
+*/
+var MarkdownPageNumberCountError = class extends Error {
+	pageCount;
+	pageNumberCount;
+	constructor(pageCount, pageNumberCount) {
+		super(`pageNumbers supplies ${String(pageNumberCount)} page numbers for a document of ${String(pageCount)} pages; it must supply exactly one per page`);
+		this.name = "MarkdownPageNumberCountError";
+		this.pageCount = pageCount;
+		this.pageNumberCount = pageNumberCount;
+	}
+};
+function pageNumberParagraph(pageNumber) {
+	return {
+		kind: "paragraph",
+		runs: [{ text: pageNumberMarker(pageNumber) }],
+		styleId: markdown_codec.HTML_PREFORMATTED_STYLE_ID
+	};
+}
+function labelPages(sections, pageNumbers) {
+	let pageCount = 0;
+	const label = () => {
+		const pageNumber = pageNumbers[pageCount];
+		pageCount++;
+		return pageNumber === void 0 ? [] : [pageNumberParagraph(pageNumber)];
+	};
+	const labelled = sections.map((section, sectionIndex) => {
+		const blocks = [];
+		if (sectionIndex === 0 || section.breakType !== "continuous") blocks.push(...label());
+		for (const block of section.blocks) {
+			blocks.push(block);
+			if (block.kind === "pageBreak") blocks.push(...label());
+		}
+		return {
+			...section,
+			blocks
+		};
+	});
+	if (pageCount !== pageNumbers.length) throw new MarkdownPageNumberCountError(pageCount, pageNumbers.length);
+	return labelled;
+}
 function formulaParagraph(formula) {
 	const latex = formula.presentation?.latex;
 	if (latex === void 0) return {
@@ -53,7 +103,8 @@ function markdownTableCell(cell) {
 }
 function buildMarkdownText(document, options) {
 	if (document.kind !== "wordprocessing") throw new markdown_codec.MarkdownUnsupportedDocumentKindError(document.kind);
-	const sections = document.sections.map((section) => ({
+	const pageNumbers = options?.pageNumbers;
+	const sections = (pageNumbers === void 0 ? document.sections : labelPages(document.sections, pageNumbers)).map((section) => ({
 		...section,
 		blocks: section.blocks.map(markdownBlock)
 	}));
@@ -63,5 +114,7 @@ function buildMarkdownText(document, options) {
 	}, options);
 }
 //#endregion
+exports.MarkdownPageNumberCountError = MarkdownPageNumberCountError;
 exports.PAGE_BREAK_MARKER = PAGE_BREAK_MARKER;
 exports.buildMarkdownText = buildMarkdownText;
+exports.pageNumberMarker = pageNumberMarker;

package/dist/markdown/write.d.cts

@@ -2,6 +2,27 @@ import { ContentDocument } from "document-schema.js";
 import { WriteMarkdownOptions } from "markdown-codec";
 //#region src/markdown/write.d.ts
 declare const PAGE_BREAK_MARKER = "<!-- page break -->";
-declare function buildMarkdownText(document: ContentDocument, options?: WriteMarkdownOptions): string;
+/**
+ * The marker opening a page that `BuildMarkdownTextOptions.pageNumbers` labels: an HTML comment naming the page's number, `<!-- page 7 -->` for page 7, on a line of its own. An output-only annotation for readers of the text rather than a directive: unlike {@link PAGE_BREAK_MARKER} it states which page follows, not that a page ends, and nothing reads it back as one. Reading markdown that carries it keeps it as an ordinary HTML-comment paragraph, exactly as any other comment in a markdown source is kept, so a hand-written comment of the same shape is never mistaken for a label and lost.
+ * @param pageNumber - the number the page is labelled with, as the caller supplied it
+ * @returns the marker text
+ */
+declare function pageNumberMarker(pageNumber: number): string;
+/**
+ * `BuildMarkdownTextOptions.pageNumbers` did not supply exactly one number per page of the document. Thrown rather than labelling a prefix or padding, since a label on the wrong page is worse than none.
+ */
+declare class MarkdownPageNumberCountError extends Error {
+  readonly pageCount: number;
+  readonly pageNumberCount: number;
+  constructor(pageCount: number, pageNumberCount: number);
+}
+interface BuildMarkdownTextOptions extends WriteMarkdownOptions {
+  /**
+   * One number per page of the document, in page order, written as {@link pageNumberMarker} at the start of each page so a reader of the text can tell which page each part came from. A page starts at the beginning of the document, after every top-level page break, and at the start of every section after the first that does not continue its predecessor's page (`breakType` other than `continuous`). Omitted, no page is labelled. The pdf conversions supply it for a page-selected read (`pages`), with each page's original one-based page number, since there the position of a part no longer says which page it is.
+   * @throws MarkdownPageNumberCountError when the count differs from the document's page count
+   */
+  readonly pageNumbers?: readonly number[];
+}
+declare function buildMarkdownText(document: ContentDocument, options?: BuildMarkdownTextOptions): string;
 //#endregion
-export { PAGE_BREAK_MARKER, buildMarkdownText };
+export { BuildMarkdownTextOptions, MarkdownPageNumberCountError, PAGE_BREAK_MARKER, buildMarkdownText, pageNumberMarker };

package/dist/markdown/write.d.ts

@@ -2,6 +2,27 @@ import { ContentDocument } from "document-schema.js";
 import { WriteMarkdownOptions } from "markdown-codec";
 //#region src/markdown/write.d.ts
 declare const PAGE_BREAK_MARKER = "<!-- page break -->";
-declare function buildMarkdownText(document: ContentDocument, options?: WriteMarkdownOptions): string;
+/**
+ * The marker opening a page that `BuildMarkdownTextOptions.pageNumbers` labels: an HTML comment naming the page's number, `<!-- page 7 -->` for page 7, on a line of its own. An output-only annotation for readers of the text rather than a directive: unlike {@link PAGE_BREAK_MARKER} it states which page follows, not that a page ends, and nothing reads it back as one. Reading markdown that carries it keeps it as an ordinary HTML-comment paragraph, exactly as any other comment in a markdown source is kept, so a hand-written comment of the same shape is never mistaken for a label and lost.
+ * @param pageNumber - the number the page is labelled with, as the caller supplied it
+ * @returns the marker text
+ */
+declare function pageNumberMarker(pageNumber: number): string;
+/**
+ * `BuildMarkdownTextOptions.pageNumbers` did not supply exactly one number per page of the document. Thrown rather than labelling a prefix or padding, since a label on the wrong page is worse than none.
+ */
+declare class MarkdownPageNumberCountError extends Error {
+  readonly pageCount: number;
+  readonly pageNumberCount: number;
+  constructor(pageCount: number, pageNumberCount: number);
+}
+interface BuildMarkdownTextOptions extends WriteMarkdownOptions {
+  /**
+   * One number per page of the document, in page order, written as {@link pageNumberMarker} at the start of each page so a reader of the text can tell which page each part came from. A page starts at the beginning of the document, after every top-level page break, and at the start of every section after the first that does not continue its predecessor's page (`breakType` other than `continuous`). Omitted, no page is labelled. The pdf conversions supply it for a page-selected read (`pages`), with each page's original one-based page number, since there the position of a part no longer says which page it is.
+   * @throws MarkdownPageNumberCountError when the count differs from the document's page count
+   */
+  readonly pageNumbers?: readonly number[];
+}
+declare function buildMarkdownText(document: ContentDocument, options?: BuildMarkdownTextOptions): string;
 //#endregion
-export { PAGE_BREAK_MARKER, buildMarkdownText };
+export { BuildMarkdownTextOptions, MarkdownPageNumberCountError, PAGE_BREAK_MARKER, buildMarkdownText, pageNumberMarker };

package/dist/markdown/write.js

@@ -5,6 +5,56 @@ const MATH_BLOCK_STYLE_ID = "MathBlock";
 const MATH_INLINE_FONT_MARKER = "Cambria Math";
 const MATH_INLINE_SOURCE = "markdown:math-inline";
 const PAGE_BREAK_MARKER = "<!-- page break -->";
+/**
+* The marker opening a page that `BuildMarkdownTextOptions.pageNumbers` labels: an HTML comment naming the page's number, `<!-- page 7 -->` for page 7, on a line of its own. An output-only annotation for readers of the text rather than a directive: unlike {@link PAGE_BREAK_MARKER} it states which page follows, not that a page ends, and nothing reads it back as one. Reading markdown that carries it keeps it as an ordinary HTML-comment paragraph, exactly as any other comment in a markdown source is kept, so a hand-written comment of the same shape is never mistaken for a label and lost.
+* @param pageNumber - the number the page is labelled with, as the caller supplied it
+* @returns the marker text
+*/
+function pageNumberMarker(pageNumber) {
+	return `<!-- page ${String(pageNumber)} -->`;
+}
+/**
+* `BuildMarkdownTextOptions.pageNumbers` did not supply exactly one number per page of the document. Thrown rather than labelling a prefix or padding, since a label on the wrong page is worse than none.
+*/
+var MarkdownPageNumberCountError = class extends Error {
+	pageCount;
+	pageNumberCount;
+	constructor(pageCount, pageNumberCount) {
+		super(`pageNumbers supplies ${String(pageNumberCount)} page numbers for a document of ${String(pageCount)} pages; it must supply exactly one per page`);
+		this.name = "MarkdownPageNumberCountError";
+		this.pageCount = pageCount;
+		this.pageNumberCount = pageNumberCount;
+	}
+};
+function pageNumberParagraph(pageNumber) {
+	return {
+		kind: "paragraph",
+		runs: [{ text: pageNumberMarker(pageNumber) }],
+		styleId: HTML_PREFORMATTED_STYLE_ID
+	};
+}
+function labelPages(sections, pageNumbers) {
+	let pageCount = 0;
+	const label = () => {
+		const pageNumber = pageNumbers[pageCount];
+		pageCount++;
+		return pageNumber === void 0 ? [] : [pageNumberParagraph(pageNumber)];
+	};
+	const labelled = sections.map((section, sectionIndex) => {
+		const blocks = [];
+		if (sectionIndex === 0 || section.breakType !== "continuous") blocks.push(...label());
+		for (const block of section.blocks) {
+			blocks.push(block);
+			if (block.kind === "pageBreak") blocks.push(...label());
+		}
+		return {
+			...section,
+			blocks
+		};
+	});
+	if (pageCount !== pageNumbers.length) throw new MarkdownPageNumberCountError(pageCount, pageNumbers.length);
+	return labelled;
+}
 function formulaParagraph(formula) {
 	const latex = formula.presentation?.latex;
 	if (latex === void 0) return {
@@ -52,7 +102,8 @@ function markdownTableCell(cell) {
 }
 function buildMarkdownText(document, options) {
 	if (document.kind !== "wordprocessing") throw new MarkdownUnsupportedDocumentKindError(document.kind);
-	const sections = document.sections.map((section) => ({
+	const pageNumbers = options?.pageNumbers;
+	const sections = (pageNumbers === void 0 ? document.sections : labelPages(document.sections, pageNumbers)).map((section) => ({
 		...section,
 		blocks: section.blocks.map(markdownBlock)
 	}));
@@ -62,4 +113,4 @@ function buildMarkdownText(document, options) {
 	}, options);
 }
 //#endregion
-export { PAGE_BREAK_MARKER, buildMarkdownText };
+export { MarkdownPageNumberCountError, PAGE_BREAK_MARKER, buildMarkdownText, pageNumberMarker };

package/dist/{reconstruct-presentations-prod-X315aBmI.cjs → reconstruct-presentations-prod-CA4no_aw.cjs}

@@ -6,6 +6,7 @@ const require_ports_abort = require("./ports/abort.cjs");
 const require_layout_reconstruct_lines = require("./layout/reconstruct-lines.cjs");
 const require_layout_lattice = require("./layout/lattice.cjs");
 let document_schema_js = require("document-schema.js");
+let pdf_codec_layout = require("pdf-codec/layout");
 //#region src/layout/reconstruct-tables.ts
 function recoverTables(page, pageIndex, structure) {
 	if (structure !== void 0) {
@@ -381,17 +382,17 @@ function reconstructWordprocessing(doc, options) {
 	const structure = indexStructure(doc);
 	const sections = [];
 	let currentGroup = [];
-	let groupStartPageIndex = 0;
+	let groupStartPosition = 0;
 	for (const page of doc.pages) {
 		require_ports_abort.throwIfAborted(signal);
 		if (currentGroup.length > 0 && !samePageSize(currentGroup[0], page)) {
-			sections.push(buildSection(currentGroup, groupStartPageIndex, doc.images, headingLevels, doc.form, structure));
-			groupStartPageIndex += currentGroup.length;
+			sections.push(buildSection(currentGroup, groupStartPosition, doc.images, headingLevels, doc.form, structure));
+			groupStartPosition += currentGroup.length;
 			currentGroup = [];
 		}
 		currentGroup.push(page);
 	}
-	if (currentGroup.length > 0) sections.push(buildSection(currentGroup, groupStartPageIndex, doc.images, headingLevels, doc.form, structure));
+	if (currentGroup.length > 0) sections.push(buildSection(currentGroup, groupStartPosition, doc.images, headingLevels, doc.form, structure));
 	return {
 		kind: "wordprocessing",
 		metadata: doc.metadata,
@@ -492,12 +493,12 @@ function headingLevelOf(paragraph, levels) {
 function samePageSize(a, b) {
 	return a.widthPt === b.widthPt && a.heightPt === b.heightPt;
 }
-function buildSection(pages, startPageIndex, images, headingLevels, form, structure) {
+function buildSection(pages, startPosition, images, headingLevels, form, structure) {
 	const blocks = [];
 	const divisionByBlock = /* @__PURE__ */ new WeakMap();
 	pages.forEach((page, i) => {
 		if (i > 0) blocks.push({ kind: "pageBreak" });
-		blocks.push(...reconstructPageBlocks(page, startPageIndex + i, images, headingLevels, form, structure, divisionByBlock));
+		blocks.push(...reconstructPageBlocks(page, (0, pdf_codec_layout.sourcePageIndex)(page, startPosition + i), images, headingLevels, form, structure, divisionByBlock));
 	});
 	return {
 		pageSize: {
@@ -736,9 +737,9 @@ function appendFormFieldConstructs(blocks, form, pageIndex) {
 }
 function reconstructSpreadsheet(doc, options) {
 	const signal = options?.signal;
-	const sheets = doc.pages.map((page, index) => {
+	const sheets = doc.pages.map((page, position) => {
 		require_ports_abort.throwIfAborted(signal);
-		return reconstructSheet(page, index, options?.onCellTypeInference);
+		return reconstructSheet(page, (0, pdf_codec_layout.sourcePageIndex)(page, position), options?.onCellTypeInference);
 	});
 	return {
 		kind: "spreadsheet",
@@ -751,9 +752,9 @@ function reconstructSpreadsheet(doc, options) {
 function reconstructPresentation(doc, options) {
 	const signal = options?.signal;
 	const structure = indexStructure(doc);
-	const slides = doc.pages.map((page, pageIndex) => {
+	const slides = doc.pages.map((page, position) => {
 		require_ports_abort.throwIfAborted(signal);
-		return reconstructSlide(page, pageIndex, doc.images, structure);
+		return reconstructSlide(page, (0, pdf_codec_layout.sourcePageIndex)(page, position), doc.images, structure);
 	});
 	return {
 		kind: "presentation",
@@ -933,9 +934,9 @@ function imageToShape(img, slideHeightPt, pageIndex, images) {
 }
 function reconstructDrawing(doc, options) {
 	const signal = options?.signal;
-	const pages = doc.pages.map((page, pageIndex) => {
+	const pages = doc.pages.map((page, position) => {
 		require_ports_abort.throwIfAborted(signal);
-		return reconstructDrawPage(page, pageIndex, doc.images);
+		return reconstructDrawPage(page, (0, pdf_codec_layout.sourcePageIndex)(page, position), doc.images);
 	});
 	return {
 		kind: "drawing",

package/dist/{reconstruct-presentations-prod-B5fkPiRZ.js → reconstruct-presentations-prod-CC8ct-5O.js}

@@ -6,6 +6,7 @@ import { throwIfAborted } from "./ports/abort.js";
 import { HALF_POINT_BUCKET_PT, bucketCounts, clusterIntoLines, clusterIntoParagraphs, estimateModalLineSpacing, fontSizesClose, gapExceeds, lineBox, modeOf, paragraphToContentParagraph, pushRunsForLine, textBoxOfItem, textItemToContentRun, textItemVerticalExtent } from "./layout/reconstruct-lines.js";
 import { detectGridLattice, findColumnIndex, findRowIndex } from "./layout/lattice.js";
 import { denseTableRows } from "document-schema.js";
+import { sourcePageIndex } from "pdf-codec/layout";
 //#region src/layout/reconstruct-tables.ts
 function recoverTables(page, pageIndex, structure) {
 	if (structure !== void 0) {
@@ -381,17 +382,17 @@ function reconstructWordprocessing(doc, options) {
 	const structure = indexStructure(doc);
 	const sections = [];
 	let currentGroup = [];
-	let groupStartPageIndex = 0;
+	let groupStartPosition = 0;
 	for (const page of doc.pages) {
 		throwIfAborted(signal);
 		if (currentGroup.length > 0 && !samePageSize(currentGroup[0], page)) {
-			sections.push(buildSection(currentGroup, groupStartPageIndex, doc.images, headingLevels, doc.form, structure));
-			groupStartPageIndex += currentGroup.length;
+			sections.push(buildSection(currentGroup, groupStartPosition, doc.images, headingLevels, doc.form, structure));
+			groupStartPosition += currentGroup.length;
 			currentGroup = [];
 		}
 		currentGroup.push(page);
 	}
-	if (currentGroup.length > 0) sections.push(buildSection(currentGroup, groupStartPageIndex, doc.images, headingLevels, doc.form, structure));
+	if (currentGroup.length > 0) sections.push(buildSection(currentGroup, groupStartPosition, doc.images, headingLevels, doc.form, structure));
 	return {
 		kind: "wordprocessing",
 		metadata: doc.metadata,
@@ -492,12 +493,12 @@ function headingLevelOf(paragraph, levels) {
 function samePageSize(a, b) {
 	return a.widthPt === b.widthPt && a.heightPt === b.heightPt;
 }
-function buildSection(pages, startPageIndex, images, headingLevels, form, structure) {
+function buildSection(pages, startPosition, images, headingLevels, form, structure) {
 	const blocks = [];
 	const divisionByBlock = /* @__PURE__ */ new WeakMap();
 	pages.forEach((page, i) => {
 		if (i > 0) blocks.push({ kind: "pageBreak" });
-		blocks.push(...reconstructPageBlocks(page, startPageIndex + i, images, headingLevels, form, structure, divisionByBlock));
+		blocks.push(...reconstructPageBlocks(page, sourcePageIndex(page, startPosition + i), images, headingLevels, form, structure, divisionByBlock));
 	});
 	return {
 		pageSize: {
@@ -736,9 +737,9 @@ function appendFormFieldConstructs(blocks, form, pageIndex) {
 }
 function reconstructSpreadsheet(doc, options) {
 	const signal = options?.signal;
-	const sheets = doc.pages.map((page, index) => {
+	const sheets = doc.pages.map((page, position) => {
 		throwIfAborted(signal);
-		return reconstructSheet(page, index, options?.onCellTypeInference);
+		return reconstructSheet(page, sourcePageIndex(page, position), options?.onCellTypeInference);
 	});
 	return {
 		kind: "spreadsheet",
@@ -751,9 +752,9 @@ function reconstructSpreadsheet(doc, options) {
 function reconstructPresentation(doc, options) {
 	const signal = options?.signal;
 	const structure = indexStructure(doc);
-	const slides = doc.pages.map((page, pageIndex) => {
+	const slides = doc.pages.map((page, position) => {
 		throwIfAborted(signal);
-		return reconstructSlide(page, pageIndex, doc.images, structure);
+		return reconstructSlide(page, sourcePageIndex(page, position), doc.images, structure);
 	});
 	return {
 		kind: "presentation",
@@ -933,9 +934,9 @@ function imageToShape(img, slideHeightPt, pageIndex, images) {
 }
 function reconstructDrawing(doc, options) {
 	const signal = options?.signal;
-	const pages = doc.pages.map((page, pageIndex) => {
+	const pages = doc.pages.map((page, position) => {
 		throwIfAborted(signal);
-		return reconstructDrawPage(page, pageIndex, doc.images);
+		return reconstructDrawPage(page, sourcePageIndex(page, position), doc.images);
 	});
 	return {
 		kind: "drawing",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "js.documents",
-  "version": "14.4.123",
+  "version": "14.5.0",
   "description": "Converts between docx, pptx, odt, odp, ods, odg, xlsx, csv, svg, markdown, rtf, doc, xls, ppt and PDF through one shared, Zod-typed content schema (wpd read-only), plus read+write editors for OOXML and OpenDocument. Worker-isomorphic.",
   "type": "module",
   "repository": {
@@ -85,8 +85,8 @@
     "fflate": "0.8.3",
     "markdown-codec": "11.1.16",
     "odf.js": "11.2.2",
-    "ooxml.js": "12.2.31",
-    "pdf-codec": "5.3.31",
+    "ooxml.js": "12.2.32",
+    "pdf-codec": "5.4.0",
     "ppt-codec": "2.2.23",
     "rtf-codec": "8.1.24",
     "temml": "0.13.4",