documents.js 2.1.0 → 2.3.0

package/dist/markdown/math.js

@@ -0,0 +1,109 @@
+import { buildFormulaBlock } from "../model/formula.js";
+import { extractSymbolDefinitionsFromProse } from "../latex/symbols.js";
+import { latexToFormula } from "../latex/lower.js";
+//#region src/markdown/math.ts
+const MATH_BLOCK_STYLE_ID = "MathBlock";
+const MATH_INLINE_FONT_MARKER = "Cambria Math";
+const STAND_IN_FRAME = {
+	xPt: 0,
+	yPt: 0,
+	widthPt: 0,
+	heightPt: 22
+};
+const MATH_BLOCK_SOURCE = "markdown:math-block";
+const MATH_INLINE_SOURCE = "markdown:math-inline";
+function extractInlineMath(runs) {
+	const latexRuns = [];
+	const remainingRuns = [];
+	for (const run of runs) {
+		if (run.fontFamily === MATH_INLINE_FONT_MARKER && run.text.trim() !== "") {
+			latexRuns.push(run.text);
+			continue;
+		}
+		remainingRuns.push(run);
+	}
+	const consumed = latexRuns.length > 0 && remainingRuns.every((run) => run.text === "");
+	return {
+		latexRuns,
+		remainingRuns: consumed ? [] : remainingRuns,
+		consumed
+	};
+}
+function lowerMarkdownMath(document, options) {
+	if (document.kind !== "wordprocessing") return document;
+	const sink = options?.onDiagnostic;
+	const proseEntries = extractSymbolDefinitionsFromProse(document, sink);
+	const known = new Map(proseEntries.map((entry) => [entry.glyph, entry]));
+	const minted = /* @__PURE__ */ new Map();
+	const lowerOne = (latex, source) => {
+		if (latex.trim() === "") return;
+		const result = latexToFormula(latex, {
+			symbolEntries: [...known.values()],
+			source
+		});
+		for (const diagnostic of result.diagnostics) sink?.(diagnostic);
+		for (const entry of result.mintedSymbols) if (!known.has(entry.glyph) && !minted.has(entry.glyph)) minted.set(entry.glyph, entry);
+		return buildFormulaBlock(result.formula, STAND_IN_FRAME, source);
+	};
+	const lowerBlocks = (blocks) => {
+		const out = [];
+		for (const block of blocks) {
+			if (block.kind === "table") {
+				out.push({
+					...block,
+					rows: block.rows.map((row) => ({
+						...row,
+						cells: row.cells.map((cell) => ({
+							...cell,
+							blocks: lowerBlocks(cell.blocks)
+						}))
+					}))
+				});
+				continue;
+			}
+			if (block.kind !== "paragraph") {
+				out.push(block);
+				continue;
+			}
+			if (block.styleId === MATH_BLOCK_STYLE_ID) {
+				const latex = block.runs.map((run) => run.text).join("");
+				const formulaBlock = lowerOne(latex, MATH_BLOCK_SOURCE);
+				out.push(formulaBlock ?? block);
+				continue;
+			}
+			const extraction = extractInlineMath(block.runs);
+			if (extraction.latexRuns.length === 0) {
+				out.push(block);
+				continue;
+			}
+			if (!extraction.consumed) out.push({
+				...block,
+				runs: [...extraction.remainingRuns]
+			});
+			for (const latex of extraction.latexRuns) {
+				const formulaBlock = lowerOne(latex, MATH_INLINE_SOURCE);
+				if (formulaBlock !== void 0) out.push(formulaBlock);
+			}
+		}
+		return out;
+	};
+	const sections = document.sections.map((section) => ({
+		...section,
+		blocks: lowerBlocks(section.blocks)
+	}));
+	const symbols = [...known.values(), ...minted.values()];
+	if (symbols.length === 0) return {
+		...document,
+		sections
+	};
+	return {
+		...document,
+		sections,
+		symbolTable: {
+			symbols,
+			units: []
+		}
+	};
+}
+//#endregion
+export { lowerMarkdownMath };

package/dist/markdown/read.cjs

@@ -1,13 +1,14 @@
 Object.defineProperty(exports, Symbol.toStringTag, { value: "Module" });
+const require_markdown_math = require("./math.cjs");
 let markdown_codec = require("markdown-codec");
 //#region src/markdown/read.ts
-function readMarkdownContent(text, options) {
+function readMarkdownContent(text, options, math) {
 	const { document } = (0, markdown_codec.readMarkdown)(text, {
 		frontMatter: true,
 		...options
 	});
 	if (document.kind !== "wordprocessing") throw new Error("readMarkdown returned a non-wordprocessing ContentDocument");
-	return document;
+	return require_markdown_math.lowerMarkdownMath(document, math);
 }
 //#endregion
 exports.readMarkdownContent = readMarkdownContent;

package/dist/markdown/read.d.cts

@@ -1,6 +1,7 @@
+import { MarkdownMathLoweringOptions } from "./math.cjs";
 import { ContentDocument } from "document-schema.js";
 import { ReadMarkdownOptions } from "markdown-codec";
 //#region src/markdown/read.d.ts
-declare function readMarkdownContent(text: string, options?: ReadMarkdownOptions): ContentDocument;
+declare function readMarkdownContent(text: string, options?: ReadMarkdownOptions, math?: MarkdownMathLoweringOptions): ContentDocument;
 //#endregion
 export { readMarkdownContent };

package/dist/markdown/read.d.ts

@@ -1,6 +1,7 @@
+import { MarkdownMathLoweringOptions } from "./math.js";
 import { ContentDocument } from "document-schema.js";
 import { ReadMarkdownOptions } from "markdown-codec";
 //#region src/markdown/read.d.ts
-declare function readMarkdownContent(text: string, options?: ReadMarkdownOptions): ContentDocument;
+declare function readMarkdownContent(text: string, options?: ReadMarkdownOptions, math?: MarkdownMathLoweringOptions): ContentDocument;
 //#endregion
 export { readMarkdownContent };

package/dist/markdown/read.js

@@ -1,12 +1,13 @@
+import { lowerMarkdownMath } from "./math.js";
 import { readMarkdown } from "markdown-codec";
 //#region src/markdown/read.ts
-function readMarkdownContent(text, options) {
+function readMarkdownContent(text, options, math) {
 	const { document } = readMarkdown(text, {
 		frontMatter: true,
 		...options
 	});
 	if (document.kind !== "wordprocessing") throw new Error("readMarkdown returned a non-wordprocessing ContentDocument");
-	return document;
+	return lowerMarkdownMath(document, math);
 }
 //#endregion
 export { readMarkdownContent };

package/dist/markdown/write.cjs

@@ -2,6 +2,28 @@ Object.defineProperty(exports, Symbol.toStringTag, { value: "Module" });
 const require_model_formula = require("../model/formula.cjs");
 let markdown_codec = require("markdown-codec");
 //#region src/markdown/write.ts
+const MATH_BLOCK_STYLE_ID = "MathBlock";
+const MATH_INLINE_FONT_MARKER = "Cambria Math";
+const MATH_INLINE_SOURCE = "markdown:math-inline";
+function formulaParagraph(formula) {
+	const latex = formula.presentation?.latex;
+	if (latex === void 0) return {
+		kind: "paragraph",
+		runs: [{ text: require_model_formula.formulaPlaceholderText(formula) }]
+	};
+	if (formula.provenance?.source === MATH_INLINE_SOURCE) return {
+		kind: "paragraph",
+		runs: [{
+			text: latex,
+			fontFamily: MATH_INLINE_FONT_MARKER
+		}]
+	};
+	return {
+		kind: "paragraph",
+		runs: [{ text: latex }],
+		styleId: MATH_BLOCK_STYLE_ID
+	};
+}
 function markdownBlock(block) {
 	if (block.kind === "table") return {
 		...block,
@@ -12,10 +34,7 @@ function markdownBlock(block) {
 	};
 	if (block.kind === "embeddedObject") {
 		const formula = require_model_formula.formulaOfBlock(block);
-		if (formula !== void 0) return {
-			kind: "paragraph",
-			runs: [{ text: require_model_formula.formulaPlaceholderText(formula) }]
-		};
+		if (formula !== void 0) return formulaParagraph(formula);
 		return block;
 	}
 	return block;

package/dist/markdown/write.js

@@ -1,6 +1,28 @@
 import { formulaOfBlock, formulaPlaceholderText } from "../model/formula.js";
 import { MarkdownUnsupportedDocumentKindError, writeMarkdown } from "markdown-codec";
 //#region src/markdown/write.ts
+const MATH_BLOCK_STYLE_ID = "MathBlock";
+const MATH_INLINE_FONT_MARKER = "Cambria Math";
+const MATH_INLINE_SOURCE = "markdown:math-inline";
+function formulaParagraph(formula) {
+	const latex = formula.presentation?.latex;
+	if (latex === void 0) return {
+		kind: "paragraph",
+		runs: [{ text: formulaPlaceholderText(formula) }]
+	};
+	if (formula.provenance?.source === MATH_INLINE_SOURCE) return {
+		kind: "paragraph",
+		runs: [{
+			text: latex,
+			fontFamily: MATH_INLINE_FONT_MARKER
+		}]
+	};
+	return {
+		kind: "paragraph",
+		runs: [{ text: latex }],
+		styleId: MATH_BLOCK_STYLE_ID
+	};
+}
 function markdownBlock(block) {
 	if (block.kind === "table") return {
 		...block,
@@ -11,10 +33,7 @@ function markdownBlock(block) {
 	};
 	if (block.kind === "embeddedObject") {
 		const formula = formulaOfBlock(block);
-		if (formula !== void 0) return {
-			kind: "paragraph",
-			runs: [{ text: formulaPlaceholderText(formula) }]
-		};
+		if (formula !== void 0) return formulaParagraph(formula);
 		return block;
 	}
 	return block;

package/dist/metadata/write.cjs

@@ -39,6 +39,7 @@ function classifyWritePath(source, target) {
 	if (source === "pdf" && target === "pdf") return { kind: "pdf" };
 	if (target === "odf" || source === "odf") return { errorMessage: "'odf' (a standalone formula document) is not a supported setDocumentMetadata source or target -- it has no write path back out at all" };
 	if (target === "csv" || source === "csv") return { errorMessage: "'csv' is not a supported setDocumentMetadata source or target -- RFC 4180 text has no metadata container, so a rebuild would silently drop the override. Convert to or from csv first, then patch metadata on the package format." };
+	if (target === "svg" || source === "svg") return { errorMessage: "'svg' is not a supported setDocumentMetadata source or target -- this package's SVG metadata surface is the root <title> element alone, so an author/subject/keywords override would be silently dropped by the rebuild. Convert to or from svg first, then patch metadata on the package format." };
 	if (!isRebuildFormat(source) || !isRebuildFormat(target)) return { errorMessage: `setDocumentMetadata only patches metadata in place; it does not convert format -- source ('${source}') and target ('${target}') must be the same format (or both 'pdf'). Convert first if you need a different target format.` };
 	if (source !== target) return { errorMessage: `setDocumentMetadata only patches metadata in place; it does not convert format -- source ('${source}') and target ('${target}') must be the same format. Convert first if you need a different target format.` };
 	return {

package/dist/metadata/write.js

@@ -38,6 +38,7 @@ function classifyWritePath(source, target) {
 	if (source === "pdf" && target === "pdf") return { kind: "pdf" };
 	if (target === "odf" || source === "odf") return { errorMessage: "'odf' (a standalone formula document) is not a supported setDocumentMetadata source or target -- it has no write path back out at all" };
 	if (target === "csv" || source === "csv") return { errorMessage: "'csv' is not a supported setDocumentMetadata source or target -- RFC 4180 text has no metadata container, so a rebuild would silently drop the override. Convert to or from csv first, then patch metadata on the package format." };
+	if (target === "svg" || source === "svg") return { errorMessage: "'svg' is not a supported setDocumentMetadata source or target -- this package's SVG metadata surface is the root <title> element alone, so an author/subject/keywords override would be silently dropped by the rebuild. Convert to or from svg first, then patch metadata on the package format." };
 	if (!isRebuildFormat(source) || !isRebuildFormat(target)) return { errorMessage: `setDocumentMetadata only patches metadata in place; it does not convert format -- source ('${source}') and target ('${target}') must be the same format (or both 'pdf'). Convert first if you need a different target format.` };
 	if (source !== target) return { errorMessage: `setDocumentMetadata only patches metadata in place; it does not convert format -- source ('${source}') and target ('${target}') must be the same format. Convert first if you need a different target format.` };
 	return {

package/dist/model/bytes.cjs

@@ -90,6 +90,10 @@ function isWellFormedUtf8Text(bytes) {
 }
 const MarkdownBytesSchema = zod.z.instanceof(Uint8Array).refine(isWellFormedUtf8Text, { message: "not well-formed UTF-8 text" });
 const CsvBytesSchema = zod.z.instanceof(Uint8Array).refine(isWellFormedUtf8Text, { message: "not well-formed UTF-8 text" });
+const SvgBytesSchema = zod.z.instanceof(Uint8Array).refine((bytes) => {
+	if (!isWellFormedUtf8Text(bytes)) return false;
+	return new TextDecoder().decode(bytes).toLowerCase().includes("<svg");
+}, { message: "not a valid SVG file: not well-formed UTF-8 text containing an <svg root element" });
 //#endregion
 exports.CsvBytesSchema = CsvBytesSchema;
 exports.DocxBytesSchema = DocxBytesSchema;
@@ -100,4 +104,5 @@ exports.OdsBytesSchema = OdsBytesSchema;
 exports.OdtBytesSchema = OdtBytesSchema;
 exports.PdfBytesSchema = PdfBytesSchema;
 exports.PptxBytesSchema = PptxBytesSchema;
+exports.SvgBytesSchema = SvgBytesSchema;
 exports.XlsxBytesSchema = XlsxBytesSchema;

package/dist/model/bytes.d.cts

@@ -10,5 +10,6 @@ declare const OdpBytesSchema: z.ZodCustom<Uint8Array<ArrayBuffer>, Uint8Array<Ar
 declare const OdgBytesSchema: z.ZodCustom<Uint8Array<ArrayBuffer>, Uint8Array<ArrayBuffer>>;
 declare const MarkdownBytesSchema: z.ZodCustom<Uint8Array<ArrayBuffer>, Uint8Array<ArrayBuffer>>;
 declare const CsvBytesSchema: z.ZodCustom<Uint8Array<ArrayBuffer>, Uint8Array<ArrayBuffer>>;
+declare const SvgBytesSchema: z.ZodCustom<Uint8Array<ArrayBuffer>, Uint8Array<ArrayBuffer>>;
 //#endregion
-export { CsvBytesSchema, DocxBytesSchema, MarkdownBytesSchema, OdgBytesSchema, OdpBytesSchema, OdsBytesSchema, OdtBytesSchema, PdfBytesSchema, PptxBytesSchema, XlsxBytesSchema };
+export { CsvBytesSchema, DocxBytesSchema, MarkdownBytesSchema, OdgBytesSchema, OdpBytesSchema, OdsBytesSchema, OdtBytesSchema, PdfBytesSchema, PptxBytesSchema, SvgBytesSchema, XlsxBytesSchema };

package/dist/model/bytes.d.ts

@@ -10,5 +10,6 @@ declare const OdpBytesSchema: z.ZodCustom<Uint8Array<ArrayBuffer>, Uint8Array<Ar
 declare const OdgBytesSchema: z.ZodCustom<Uint8Array<ArrayBuffer>, Uint8Array<ArrayBuffer>>;
 declare const MarkdownBytesSchema: z.ZodCustom<Uint8Array<ArrayBuffer>, Uint8Array<ArrayBuffer>>;
 declare const CsvBytesSchema: z.ZodCustom<Uint8Array<ArrayBuffer>, Uint8Array<ArrayBuffer>>;
+declare const SvgBytesSchema: z.ZodCustom<Uint8Array<ArrayBuffer>, Uint8Array<ArrayBuffer>>;
 //#endregion
-export { CsvBytesSchema, DocxBytesSchema, MarkdownBytesSchema, OdgBytesSchema, OdpBytesSchema, OdsBytesSchema, OdtBytesSchema, PdfBytesSchema, PptxBytesSchema, XlsxBytesSchema };
+export { CsvBytesSchema, DocxBytesSchema, MarkdownBytesSchema, OdgBytesSchema, OdpBytesSchema, OdsBytesSchema, OdtBytesSchema, PdfBytesSchema, PptxBytesSchema, SvgBytesSchema, XlsxBytesSchema };

package/dist/model/bytes.js

@@ -89,5 +89,9 @@ function isWellFormedUtf8Text(bytes) {
 }
 const MarkdownBytesSchema = z.instanceof(Uint8Array).refine(isWellFormedUtf8Text, { message: "not well-formed UTF-8 text" });
 const CsvBytesSchema = z.instanceof(Uint8Array).refine(isWellFormedUtf8Text, { message: "not well-formed UTF-8 text" });
+const SvgBytesSchema = z.instanceof(Uint8Array).refine((bytes) => {
+	if (!isWellFormedUtf8Text(bytes)) return false;
+	return new TextDecoder().decode(bytes).toLowerCase().includes("<svg");
+}, { message: "not a valid SVG file: not well-formed UTF-8 text containing an <svg root element" });
 //#endregion
-export { CsvBytesSchema, DocxBytesSchema, MarkdownBytesSchema, OdgBytesSchema, OdpBytesSchema, OdsBytesSchema, OdtBytesSchema, PdfBytesSchema, PptxBytesSchema, XlsxBytesSchema };
+export { CsvBytesSchema, DocxBytesSchema, MarkdownBytesSchema, OdgBytesSchema, OdpBytesSchema, OdsBytesSchema, OdtBytesSchema, PdfBytesSchema, PptxBytesSchema, SvgBytesSchema, XlsxBytesSchema };

package/dist/model/formula.cjs

@@ -22,7 +22,7 @@ function formulaOfBlock(block) {
 	return block.document.kind === "formula" ? block.document.formula : void 0;
 }
 function formulaPlaceholderText(formula) {
-	return formula.starMath ?? "[formula]";
+	return formula.starMath ?? formula.presentation?.latex ?? "[formula]";
 }
 //#endregion
 exports.buildFormulaBlock = buildFormulaBlock;

package/dist/model/formula.js

@@ -21,7 +21,7 @@ function formulaOfBlock(block) {
 	return block.document.kind === "formula" ? block.document.formula : void 0;
 }
 function formulaPlaceholderText(formula) {
-	return formula.starMath ?? "[formula]";
+	return formula.starMath ?? formula.presentation?.latex ?? "[formula]";
 }
 //#endregion
 export { buildFormulaBlock, formulaDocument, formulaOfBlock, formulaPlaceholderText };

package/dist/svg/diagnostics.cjs

@@ -0,0 +1,19 @@
+Object.defineProperty(exports, Symbol.toStringTag, { value: "Module" });
+//#region src/svg/diagnostics.ts
+const SVG_DIAGNOSTIC_CODES = [
+	"svg/text-unsupported",
+	"svg/image-unsupported",
+	"svg/use-unsupported",
+	"svg/gradient-unsupported",
+	"svg/element-unsupported",
+	"svg/element-skipped",
+	"svg/css-style-ignored",
+	"svg/paint-unsupported",
+	"svg/opacity-ignored",
+	"svg/preserve-aspect-ratio-stretched",
+	"svg/default-size-assumed",
+	"svg/shape-unsupported",
+	"svg/stroke-style-unsupported"
+];
+//#endregion
+exports.SVG_DIAGNOSTIC_CODES = SVG_DIAGNOSTIC_CODES;

package/dist/svg/diagnostics.d.cts

@@ -0,0 +1,10 @@
+//#region src/svg/diagnostics.d.ts
+declare const SVG_DIAGNOSTIC_CODES: readonly ["svg/text-unsupported", "svg/image-unsupported", "svg/use-unsupported", "svg/gradient-unsupported", "svg/element-unsupported", "svg/element-skipped", "svg/css-style-ignored", "svg/paint-unsupported", "svg/opacity-ignored", "svg/preserve-aspect-ratio-stretched", "svg/default-size-assumed", "svg/shape-unsupported", "svg/stroke-style-unsupported"];
+type SvgDiagnosticCode = (typeof SVG_DIAGNOSTIC_CODES)[number];
+interface SvgDiagnostic {
+  readonly code: SvgDiagnosticCode;
+  readonly detail?: string;
+}
+type SvgDiagnosticSink = (diagnostic: SvgDiagnostic) => void;
+//#endregion
+export { SVG_DIAGNOSTIC_CODES, SvgDiagnostic, SvgDiagnosticCode, SvgDiagnosticSink };

package/dist/svg/diagnostics.d.ts

@@ -0,0 +1,10 @@
+//#region src/svg/diagnostics.d.ts
+declare const SVG_DIAGNOSTIC_CODES: readonly ["svg/text-unsupported", "svg/image-unsupported", "svg/use-unsupported", "svg/gradient-unsupported", "svg/element-unsupported", "svg/element-skipped", "svg/css-style-ignored", "svg/paint-unsupported", "svg/opacity-ignored", "svg/preserve-aspect-ratio-stretched", "svg/default-size-assumed", "svg/shape-unsupported", "svg/stroke-style-unsupported"];
+type SvgDiagnosticCode = (typeof SVG_DIAGNOSTIC_CODES)[number];
+interface SvgDiagnostic {
+  readonly code: SvgDiagnosticCode;
+  readonly detail?: string;
+}
+type SvgDiagnosticSink = (diagnostic: SvgDiagnostic) => void;
+//#endregion
+export { SVG_DIAGNOSTIC_CODES, SvgDiagnostic, SvgDiagnosticCode, SvgDiagnosticSink };

package/dist/svg/diagnostics.js

@@ -0,0 +1,18 @@
+//#region src/svg/diagnostics.ts
+const SVG_DIAGNOSTIC_CODES = [
+	"svg/text-unsupported",
+	"svg/image-unsupported",
+	"svg/use-unsupported",
+	"svg/gradient-unsupported",
+	"svg/element-unsupported",
+	"svg/element-skipped",
+	"svg/css-style-ignored",
+	"svg/paint-unsupported",
+	"svg/opacity-ignored",
+	"svg/preserve-aspect-ratio-stretched",
+	"svg/default-size-assumed",
+	"svg/shape-unsupported",
+	"svg/stroke-style-unsupported"
+];
+//#endregion
+export { SVG_DIAGNOSTIC_CODES };