keepset 0.19.0 → 0.20.0

package/dist/{bundled-8oHQPxcd.js → bundled-BmqpHjOH.js}

@@ -410,7 +410,7 @@ const CitationSchema = z.object({
 const RelativePathSchema = z.string().refine((path) => path.split("/").every((segment) => segment !== "" && segment !== "." && segment !== ".."), { message: "must be a relative path of non-empty segments with no '.' or '..'" });
 /** Which file of an archive to read: a member path, matched against a member's whole path or its trailing segments (so `net.gml` finds `net/net.gml`), or the member whose name ends with one of a list of extensions (a format can have several, such as Pajek's `.net` and `.paj`). Either must match exactly one member when the recipe runs; macOS resource-fork members (`__MACOSX/` and `._` files) never match. */
 const ArchiveMemberSchema = z.union([z.object({ path: RelativePathSchema }).strict(), z.object({ extensions: z.array(z.string().regex(/^\.[A-Za-z0-9][A-Za-z0-9.]*$/, { message: "must be a file extension such as .mtx" })).min(1) }).strict()]);
-/** How the downloaded bytes unpack into the one file the parser reads. */
+/** How the downloaded bytes unpack into the one file the parser reads. A workbook (`xlsx`) is read as the CSV of its named sheet, with dates as ISO 8601 text, for the `csv-table` parser. */
 const ArchiveSchema = z.discriminatedUnion("kind", [
 	z.object({ kind: z.literal("none") }).strict(),
 	z.object({ kind: z.literal("gzip") }).strict(),
@@ -425,6 +425,10 @@ const ArchiveSchema = z.discriminatedUnion("kind", [
 	z.object({
 		kind: z.literal("tar.gz"),
 		member: ArchiveMemberSchema
+	}).strict(),
+	z.object({
+		kind: z.literal("xlsx"),
+		sheet: z.string().min(1)
 	}).strict()
 ]);
 const ColumnSchema = z.int().min(0);
@@ -889,7 +893,7 @@ var catalogue_default = {
 		"id": "keepset",
 		"name": "keepset",
 		"description": "The keepset catalogue: datasets with machine-readable recipes that fetch each one and normalise it into its category's target shape.",
-		"version": "1.7.0",
+		"version": "1.8.0",
 		"repository": "https://github.com/Mearman/keepset",
 		"namespaceAliases": {
 			"networkrepository": ["nr"],
@@ -5191,6 +5195,10 @@ var catalogue_default = {
 				"url": "https://environment.data.gov.uk/dataset/9c7728fc-68e2-46e1-addb-63790b6b5313",
 				"retrieved": "2026-10-19",
 				"status": "live"
+			}, {
+				"url": "https://environment.data.gov.uk/api/file/download?fileDataSetId=e06036f5-7f41-46a3-93ff-fbd0fa1a83cc&fileName=Environment_Agency_Prosecutions.xlsx",
+				"retrieved": "2026-10-19",
+				"status": "live"
 			}],
 			"licence": {
 				"kind": "spdx",
@@ -5198,10 +5206,73 @@ var catalogue_default = {
 			},
 			"citations": [],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "The download is an xlsx workbook with an explanation sheet and a data sheet, and keepset has no spreadsheet parser yet."
+				"status": "fetchable",
+				"source": 1,
+				"archive": {
+					"kind": "xlsx",
+					"sheet": "Environment Agency Prosecutions"
+				},
+				"parser": {
+					"format": "csv-table",
+					"encoding": "utf-8",
+					"delimiter": "comma",
+					"skipLines": 0,
+					"idColumn": null,
+					"numericColumns": [{
+						"column": "Fine",
+						"factor": 1
+					}],
+					"columns": [
+						"Date_of_Action",
+						"Fine",
+						"Incident_Type",
+						"Verdict",
+						"Incident_Area"
+					]
+				}
+			},
+			"crosswalk": {
+				"source": "csv-table",
+				"target": "or/v1",
+				"rules": [
+					{
+						"op": "move",
+						"from": "meta",
+						"to": "meta"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].id",
+						"to": "nodes[].id"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].Date_of_Action",
+						"to": "nodes[].closed"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].Fine",
+						"to": "nodes[].prize"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].Incident_Type",
+						"to": "nodes[].skill"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].Verdict",
+						"to": "nodes[].status"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].Incident_Area",
+						"to": "nodes[].territory"
+					}
+				],
+				"oneWay": []
 			},
-			"crosswalk": { "file": "crosswalks/or-v1/nodes.json" },
 			"expectedCounts": {},
 			"properties": { "surveyId": "or-50" }
 		},

package/dist/{categories-tH53cHmu.d.ts → categories-BVROO4tM.d.ts}

@@ -70,7 +70,7 @@ declare const ArchiveMemberSchema: z.ZodUnion<readonly [z.ZodObject<{
   extensions: z.ZodArray<z.ZodString>;
 }, z.core.$strict>]>;
 type ArchiveMember = z.infer<typeof ArchiveMemberSchema>;
-/** How the downloaded bytes unpack into the one file the parser reads. */
+/** How the downloaded bytes unpack into the one file the parser reads. A workbook (`xlsx`) is read as the CSV of its named sheet, with dates as ISO 8601 text, for the `csv-table` parser. */
 declare const ArchiveSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
   kind: z.ZodLiteral<"none">;
 }, z.core.$strict>, z.ZodObject<{
@@ -96,6 +96,9 @@ declare const ArchiveSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
   }, z.core.$strict>, z.ZodObject<{
     extensions: z.ZodArray<z.ZodString>;
   }, z.core.$strict>]>;
+}, z.core.$strict>, z.ZodObject<{
+  kind: z.ZodLiteral<"xlsx">;
+  sheet: z.ZodString;
 }, z.core.$strict>], "kind">;
 type Archive = z.infer<typeof ArchiveSchema>;
 /** A column of a table as the table parser names it: the header with every run of characters outside letters, digits and underscore replaced by one underscore, so it is a valid segment of a twindex path. */
@@ -199,6 +202,9 @@ declare const RecipeSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
     }, z.core.$strict>, z.ZodObject<{
       extensions: z.ZodArray<z.ZodString>;
     }, z.core.$strict>]>;
+  }, z.core.$strict>, z.ZodObject<{
+    kind: z.ZodLiteral<"xlsx">;
+    sheet: z.ZodString;
   }, z.core.$strict>], "kind">;
   parser: z.ZodDiscriminatedUnion<[z.ZodObject<{
     format: z.ZodLiteral<"edge-list">;
@@ -352,6 +358,9 @@ declare const EntrySchema: z.ZodObject<{
       }, z.core.$strict>, z.ZodObject<{
         extensions: z.ZodArray<z.ZodString>;
       }, z.core.$strict>]>;
+    }, z.core.$strict>, z.ZodObject<{
+      kind: z.ZodLiteral<"xlsx">;
+      sheet: z.ZodString;
     }, z.core.$strict>], "kind">;
     parser: z.ZodDiscriminatedUnion<[z.ZodObject<{
       format: z.ZodLiteral<"edge-list">;
@@ -486,6 +495,9 @@ declare const EntrySchema: z.ZodObject<{
         } | {
           extensions: string[];
         };
+      } | {
+        kind: "xlsx";
+        sheet: string;
       };
       parser: {
         format: "edge-list";
@@ -709,6 +721,9 @@ declare const CatalogueIndexSchema: z.ZodObject<{
         }, z.core.$strict>, z.ZodObject<{
           extensions: z.ZodArray<z.ZodString>;
         }, z.core.$strict>]>;
+      }, z.core.$strict>, z.ZodObject<{
+        kind: z.ZodLiteral<"xlsx">;
+        sheet: z.ZodString;
       }, z.core.$strict>], "kind">;
       parser: z.ZodDiscriminatedUnion<[z.ZodObject<{
         format: z.ZodLiteral<"edge-list">;
@@ -843,6 +858,9 @@ declare const CatalogueIndexSchema: z.ZodObject<{
           } | {
             extensions: string[];
           };
+        } | {
+          kind: "xlsx";
+          sheet: string;
         };
         parser: {
           format: "edge-list";
@@ -975,6 +993,9 @@ declare const CatalogueIndexSchema: z.ZodObject<{
           } | {
             extensions: string[];
           };
+        } | {
+          kind: "xlsx";
+          sheet: string;
         };
         parser: {
           format: "edge-list";

package/dist/index.d.ts

@@ -1,4 +1,4 @@
-import { $ as Parser, A as LineageSchema, B as Citation, C as CatalogueIndex, D as NamespaceNode, E as DatasetQuery, F as AliasSchema, G as Entry, H as ColumnNameSchema, I as Archive, J as IdSchema, K as EntrySchema, L as ArchiveMember, M as ManifestSchema, N as SemVerSchema, O as createCatalogue, P as parseManifest, Q as NamespaceSchema, R as ArchiveMemberSchema, S as Catalogue, T as Dataset, U as CrosswalkReference, V as CitationSchema, W as CrosswalkReferenceSchema, X as LicenceSchema, Y as Licence, Z as Namespace, _ as GraphEdgeSchema, a as CategoryTargets, at as Snapshot, b as GraphV1, c as getCategory, ct as SourceSchema, d as listCategories, dt as waybackUrl, et as ParserSchema, f as OrNode, g as GraphEdge, h as OrV1Schema, i as CategoryTarget, it as RelativePathSchema, j as Manifest, k as Lineage, l as getTarget, lt as WaybackTimestampSchema, m as OrV1, n as CategoryId, nt as Recipe, o as CountedKey, ot as SnapshotSchema, p as OrNodeSchema, q as HttpUrlSchema, r as CategoryIdSchema, rt as RecipeSchema, s as countTarget, st as Source, t as Category, tt as RESERVED_META_KEYS, u as kindOf, ut as parseEntry, v as GraphNode, w as CatalogueIndexSchema, x as GraphV1Schema, y as GraphNodeSchema, z as ArchiveSchema } from "./categories-tH53cHmu.js";
+import { $ as Parser, A as LineageSchema, B as Citation, C as CatalogueIndex, D as NamespaceNode, E as DatasetQuery, F as AliasSchema, G as Entry, H as ColumnNameSchema, I as Archive, J as IdSchema, K as EntrySchema, L as ArchiveMember, M as ManifestSchema, N as SemVerSchema, O as createCatalogue, P as parseManifest, Q as NamespaceSchema, R as ArchiveMemberSchema, S as Catalogue, T as Dataset, U as CrosswalkReference, V as CitationSchema, W as CrosswalkReferenceSchema, X as LicenceSchema, Y as Licence, Z as Namespace, _ as GraphEdgeSchema, a as CategoryTargets, at as Snapshot, b as GraphV1, c as getCategory, ct as SourceSchema, d as listCategories, dt as waybackUrl, et as ParserSchema, f as OrNode, g as GraphEdge, h as OrV1Schema, i as CategoryTarget, it as RelativePathSchema, j as Manifest, k as Lineage, l as getTarget, lt as WaybackTimestampSchema, m as OrV1, n as CategoryId, nt as Recipe, o as CountedKey, ot as SnapshotSchema, p as OrNodeSchema, q as HttpUrlSchema, r as CategoryIdSchema, rt as RecipeSchema, s as countTarget, st as Source, t as Category, tt as RESERVED_META_KEYS, u as kindOf, ut as parseEntry, v as GraphNode, w as CatalogueIndexSchema, x as GraphV1Schema, y as GraphNodeSchema, z as ArchiveSchema } from "./categories-BVROO4tM.js";
 import { Crosswalk } from "twindex";
 import { z } from "zod";
 //#region src/errors.d.ts

package/dist/index.js

@@ -1,4 +1,4 @@
-import { $ as NativeParseError, A as toIssues, B as kindOf, C as RESERVED_META_KEYS, D as SourceSchema, E as SnapshotSchema, G as GraphNodeSchema, H as OrNodeSchema, I as CategoryIdSchema, J as ArchiveError, K as GraphV1Schema, L as countTarget, M as NAME_SEPARATOR, N as groupsOf, O as WaybackTimestampSchema, P as namesOf, Q as KeepsetError, R as getCategory, S as ParserSchema, T as RelativePathSchema, U as OrV1Schema, V as listCategories, W as GraphEdgeSchema, X as DatasetAmbiguousError, Y as CatalogueSyntaxError, Z as DatasetNotFoundError, _ as EntrySchema, a as CatalogueIndexSchema, b as LicenceSchema, c as ManifestSchema, d as AliasSchema, et as RecipeError, f as ArchiveMemberSchema, g as CrosswalkReferenceSchema, h as ColumnNameSchema, i as listNamespaces, j as waybackUrl, k as parseEntry, l as SemVerSchema, m as CitationSchema, n as getManifest, o as createCatalogue, p as ArchiveSchema, q as JsonScalarSchema, r as listDatasets, s as LineageSchema, t as getDataset, tt as UnknownCategoryError, u as parseManifest, v as HttpUrlSchema, w as RecipeSchema, x as NamespaceSchema, y as IdSchema, z as getTarget } from "./bundled-8oHQPxcd.js";
+import { $ as NativeParseError, A as toIssues, B as kindOf, C as RESERVED_META_KEYS, D as SourceSchema, E as SnapshotSchema, G as GraphNodeSchema, H as OrNodeSchema, I as CategoryIdSchema, J as ArchiveError, K as GraphV1Schema, L as countTarget, M as NAME_SEPARATOR, N as groupsOf, O as WaybackTimestampSchema, P as namesOf, Q as KeepsetError, R as getCategory, S as ParserSchema, T as RelativePathSchema, U as OrV1Schema, V as listCategories, W as GraphEdgeSchema, X as DatasetAmbiguousError, Y as CatalogueSyntaxError, Z as DatasetNotFoundError, _ as EntrySchema, a as CatalogueIndexSchema, b as LicenceSchema, c as ManifestSchema, d as AliasSchema, et as RecipeError, f as ArchiveMemberSchema, g as CrosswalkReferenceSchema, h as ColumnNameSchema, i as listNamespaces, j as waybackUrl, k as parseEntry, l as SemVerSchema, m as CitationSchema, n as getManifest, o as createCatalogue, p as ArchiveSchema, q as JsonScalarSchema, r as listDatasets, s as LineageSchema, t as getDataset, tt as UnknownCategoryError, u as parseManifest, v as HttpUrlSchema, w as RecipeSchema, x as NamespaceSchema, y as IdSchema, z as getTarget } from "./bundled-BmqpHjOH.js";
 import { validateCrosswalk } from "twindex";
 //#region src/serialise.ts
 /**

package/dist/node/fetch-dataset.d.ts

@@ -1,4 +1,4 @@
-import { G as Entry, T as Dataset, at as Snapshot, i as CategoryTarget, st as Source } from "../categories-tH53cHmu.js";
+import { G as Entry, T as Dataset, at as Snapshot, i as CategoryTarget, st as Source } from "../categories-BVROO4tM.js";
 //#region src/node/fetch-dataset.d.ts
 /** The network port a recipe downloads through: `downloadRaw` by default, which returns the bytes exactly as served, or a stand-in under test. */
 export type FetchPort = (url: string, init: {

package/dist/node/fetch-dataset.js

@@ -1,4 +1,4 @@
-import { $ as NativeParseError, F as getOwn, J as ArchiveError, L as countTarget, Q as KeepsetError, et as RecipeError, t as getDataset, z as getTarget } from "../bundled-8oHQPxcd.js";
+import { $ as NativeParseError, F as getOwn, J as ArchiveError, L as countTarget, Q as KeepsetError, et as RecipeError, t as getDataset, z as getTarget } from "../bundled-BmqpHjOH.js";
 import { RoundTripMismatchError, assertRoundTrip, encode } from "twindex";
 import { z } from "zod";
 import { createHash } from "node:crypto";
@@ -356,7 +356,7 @@ const DELIMITERS = {
 	semicolon: ";"
 };
 /** A number as a decimal literal, with an optional sign and exponent. `Number` alone would also accept hex, binary, `Infinity` and the empty string. */
-const DECIMAL = /^[+-]?(?:\d+\.?\d*|\.\d+)(?:[eE][+-]?\d+)?$/;
+const DECIMAL$1 = /^[+-]?(?:\d+\.?\d*|\.\d+)(?:[eE][+-]?\d+)?$/;
 /** The byte order mark some exporters put before the first header. */
 const BYTE_ORDER_MARK = "";
 /**
@@ -559,7 +559,7 @@ function* withoutByteOrderMark(text) {
 */
 function numeric$1(cell, factor, column, line) {
 	if (cell === "") return null;
-	if (!DECIMAL.test(cell)) throw new NativeParseError("csv-table", line, `column ${column} is declared numeric but holds ${JSON.stringify(cell)}`);
+	if (!DECIMAL$1.test(cell)) throw new NativeParseError("csv-table", line, `column ${column} is declared numeric but holds ${JSON.stringify(cell)}`);
 	return Number(cell) * factor;
 }
 /**
@@ -933,7 +933,7 @@ const BYTE_RADIX = 256;
 * @param length - Field length.
 * @returns The field text.
 */
-function field(bytes, offset, length) {
+function field$1(bytes, offset, length) {
 	const slice = bytes.subarray(offset, offset + length);
 	const end = slice.indexOf(0);
 	return new TextDecoder().decode(end === -1 ? slice : slice.subarray(0, end));
@@ -952,7 +952,7 @@ function numeric(bytes, offset, length) {
 		for (const byte of bytes.subarray(offset + 1, offset + length)) value = value * BYTE_RADIX + byte;
 		return value;
 	}
-	const text = field(bytes, offset, length).trim();
+	const text = field$1(bytes, offset, length).trim();
 	if (!/^[0-7]*$/.test(text)) throw new ArchiveError(`tar header field is not octal: ${JSON.stringify(text)}`);
 	return text === "" ? 0 : Number.parseInt(text, 8);
 }
@@ -988,21 +988,21 @@ function readTar(bytes) {
 		for (const [index, byte] of header.entries()) sum += index >= checksum.offset && index < checksum.offset + checksum.length ? 32 : byte;
 		if (sum !== numeric(header, checksum.offset, checksum.length)) throw new ArchiveError(`tar header at byte ${String(offset)} fails its checksum`);
 		const size = numeric(header, HEADER.size.offset, HEADER.size.length);
-		const type = field(header, HEADER.type.offset, HEADER.type.length);
+		const type = field$1(header, HEADER.type.offset, HEADER.type.length);
 		const dataStart = offset + 512;
 		if (dataStart + size > bytes.length) throw new ArchiveError(`tar member at byte ${String(offset)} runs past the end of the archive`);
 		const data = bytes.subarray(dataStart, dataStart + size);
 		offset = dataStart + Math.ceil(size / 512) * 512;
 		if (type === "L") {
-			longName = field(data, 0, data.length);
+			longName = field$1(data, 0, data.length);
 			continue;
 		}
 		if (type === "x") {
 			longName = paxPath(data);
 			continue;
 		}
-		const name = field(header, HEADER.name.offset, HEADER.name.length);
-		const prefix = field(header, HEADER.magic.offset, HEADER.magic.length).startsWith("ustar") ? field(header, HEADER.prefix.offset, HEADER.prefix.length) : "";
+		const name = field$1(header, HEADER.name.offset, HEADER.name.length);
+		const prefix = field$1(header, HEADER.magic.offset, HEADER.magic.length).startsWith("ustar") ? field$1(header, HEADER.prefix.offset, HEADER.prefix.length) : "";
 		const path = longName ?? (prefix === "" ? name : `${prefix}/${name}`);
 		longName = void 0;
 		if (type === "0" || type === "" || type === "7") members.push({
@@ -1013,6 +1013,255 @@ function readTar(bytes) {
 	return members;
 }
 //#endregion
+//#region src/node/xlsx.ts
+const HEXADECIMAL = 16;
+const DECIMAL = 10;
+const LETTERS = 26;
+const FIRST_LETTER = "A".charCodeAt(0);
+const SECONDS_PER_DAY = 86400;
+const MILLISECONDS = 1e3;
+/** The serial number Excel gives its 29th of February 1900, a day that never existed: serials above it count from 30 December 1899 and serials below it from 31 December 1899. */
+const LEAP_BUG_SERIAL = 60;
+/** The day a serial number counts from: 1 January 1904 in a workbook that says so, otherwise 31 December 1899 for the serials before Excel's false 29th of February 1900 and 30 December 1899 for those after it. */
+const EPOCH_1904 = "1904-01-01T00:00:00Z";
+const EPOCH_BEFORE_LEAP_BUG = "1899-12-31T00:00:00Z";
+const EPOCH_AFTER_LEAP_BUG = "1899-12-30T00:00:00Z";
+const DATE_LENGTH = 10;
+const DATE_TIME_LENGTH = 19;
+const SECONDS_PER_MINUTE = 60;
+const MINUTES_PER_HOUR = 60;
+/**
+* Replaces the XML entities and character references of a text.
+* @param text - Escaped text.
+* @returns The text.
+*/
+function unescape(text) {
+	return text.replaceAll(/&(#x[0-9A-Fa-f]+|#[0-9]+|amp|lt|gt|quot|apos);/g, (_whole, entity) => {
+		if (entity.startsWith("#x")) return String.fromCodePoint(Number.parseInt(entity.slice(2), HEXADECIMAL));
+		if (entity.startsWith("#")) return String.fromCodePoint(Number.parseInt(entity.slice(1), DECIMAL));
+		return {
+			amp: "&",
+			lt: "<",
+			gt: ">",
+			quot: "\"",
+			apos: "'"
+		}[entity] ?? "";
+	});
+}
+/**
+* The attributes of a start tag's text.
+* @param tag - The text between `<` and `>`, name included.
+* @returns The attributes, unescaped.
+*/
+function attributesOf(tag) {
+	const attributes = {};
+	for (const [, name, value] of tag.matchAll(/([\w:.-]+)\s*=\s*"([^"]*)"/g)) if (name !== void 0 && value !== void 0) attributes[name] = unescape(value);
+	return attributes;
+}
+/**
+* The start tags of one element name in an XML part, in order.
+* @param xml - The part's text.
+* @param name - The element name.
+* @returns The attributes of each start tag.
+*/
+function elements(xml, name) {
+	return [...xml.matchAll(new RegExp(`<${name}(?=[\\s/>])([^>]*)>`, "g"))].map((match) => attributesOf(match[1] ?? ""));
+}
+/**
+* The strings of a workbook's shared string table, in index order: each item's text runs joined, the phonetic runs of East Asian text left out.
+* @param xml - The `sharedStrings.xml` text.
+* @returns The strings.
+*/
+function sharedStrings(xml) {
+	return [...xml.matchAll(/<si(?:\s[^>]*)?>([\s\S]*?)<\/si>/g)].map((item) => {
+		return [...(item[1] ?? "").replaceAll(/<rPh[\s\S]*?<\/rPh>/g, "").matchAll(/<t(?:\s[^>]*)?>([\s\S]*?)<\/t>/g)].map((text) => unescape(text[1] ?? "")).join("");
+	});
+}
+/** The built-in number format ids that show a date or a time, as inclusive ranges (ECMA-376, 18.8.30): the short and long dates and times, the locale dates, and the elapsed and minute times. */
+const BUILT_IN_DATE_FORMATS = [
+	{
+		first: 14,
+		last: 22
+	},
+	{
+		first: 27,
+		last: 36
+	},
+	{
+		first: 45,
+		last: 47
+	},
+	{
+		first: 50,
+		last: 58
+	}
+];
+/**
+* Whether a custom number format shows a date or a time: it names a year, month, day, hour or second once its quoted text, escaped characters and bracketed conditions and colours are removed.
+* @param code - The format code.
+* @returns True for a date or time format.
+*/
+function isDateFormat(code) {
+	return /[ymdhs]/i.test(code.replaceAll(/"[^"]*"|\\.|\[[^\]]*\]/g, ""));
+}
+/**
+* Which cell styles show dates, by the style's index.
+* @param xml - The `styles.xml` text, or undefined when the workbook has none.
+* @returns The style indexes whose number format is a date or a time.
+*/
+function dateStyles(xml) {
+	if (xml === void 0) return /* @__PURE__ */ new Set();
+	const custom = /* @__PURE__ */ new Map();
+	for (const format of elements(xml, "numFmt")) if (format["numFmtId"] !== void 0 && format["formatCode"] !== void 0) custom.set(Number(format["numFmtId"]), format["formatCode"]);
+	const cellFormats = /<cellXfs(?:\s[^>]*)?>([\s\S]*?)<\/cellXfs>/.exec(xml)?.[1] ?? "";
+	const styles = /* @__PURE__ */ new Set();
+	for (const [index, format] of elements(cellFormats, "xf").entries()) {
+		const id = Number(format["numFmtId"] ?? "0");
+		const code = custom.get(id);
+		if (code === void 0 ? BUILT_IN_DATE_FORMATS.some((range) => id >= range.first && id <= range.last) : isDateFormat(code)) styles.add(index);
+	}
+	return styles;
+}
+/**
+* A date serial number as ISO 8601 text: a date when it has no time of day, a date and time when it has, and a time alone for a serial below one day in a 1900 workbook.
+* @param serial - The serial number, with the time of day as its fraction.
+* @param date1904 - Whether the workbook counts days from 1 January 1904.
+* @returns The text.
+* @throws ArchiveError for the serial of the 29th of February 1900, which is not a date.
+*/
+function isoOf(serial, date1904) {
+	const whole = Math.floor(serial);
+	const seconds = Math.round((serial - whole) * SECONDS_PER_DAY);
+	if (!date1904 && whole === 0) return [
+		Math.floor(seconds / 3600),
+		Math.floor(seconds / SECONDS_PER_MINUTE) % MINUTES_PER_HOUR,
+		seconds % SECONDS_PER_MINUTE
+	].map((part) => String(part).padStart(2, "0")).join(":");
+	if (!date1904 && whole === LEAP_BUG_SERIAL) throw new ArchiveError("a cell holds the serial of 29 February 1900, which is not a date");
+	return new Date(Date.parse(date1904 ? EPOCH_1904 : whole < LEAP_BUG_SERIAL ? EPOCH_BEFORE_LEAP_BUG : EPOCH_AFTER_LEAP_BUG) + (whole * SECONDS_PER_DAY + seconds) * MILLISECONDS).toISOString().slice(0, seconds === 0 ? DATE_LENGTH : DATE_TIME_LENGTH);
+}
+/**
+* The 0-based column of a cell reference such as `AB12`.
+* @param reference - The reference.
+* @returns The column index.
+*/
+function columnOf(reference) {
+	let index = 0;
+	for (const letter of reference.replaceAll(/[^A-Za-z]/g, "")) index = index * LETTERS + (letter.toUpperCase().charCodeAt(0) - FIRST_LETTER + 1);
+	return index - 1;
+}
+/**
+* One CSV field: quoted when it holds a comma, a quote or a line break.
+* @param text - The cell text.
+* @returns The field.
+*/
+function field(text) {
+	return /[",\r\n]/.test(text) ? `"${text.replaceAll("\"", "\"\"")}"` : text;
+}
+/**
+* Finds the part that holds a named sheet.
+* @param workbook - The `workbook.xml` text.
+* @param rels - The workbook's relationships text.
+* @param name - The sheet's name.
+* @returns The part's path inside the archive.
+* @throws ArchiveError when the workbook has no such sheet or its relationship is missing.
+*/
+function sheetPath(workbook, rels, name) {
+	const sheets = elements(workbook, "sheet");
+	const wanted = sheets.find((sheet) => sheet["name"] === name);
+	if (wanted === void 0) throw new ArchiveError(`the workbook has no sheet ${name}; it has ${sheets.map((sheet) => sheet["name"] ?? "").join(", ")}`);
+	const target = elements(rels, "Relationship").find((relation) => relation["Id"] === wanted["r:id"])?.["Target"];
+	if (target === void 0) throw new ArchiveError(`the workbook has no relationship for the sheet ${name}`);
+	return target.startsWith("/") ? target.slice(1) : `xl/${target}`;
+}
+/**
+* Reads a worksheet's cells into text by row and column.
+* @param xml - The worksheet's text.
+* @param strings - The shared strings.
+* @param dates - The date styles.
+* @param date1904 - Whether the workbook counts days from 1 January 1904.
+* @returns The rows by 1-based row number, each a sparse list of the cells' text, and the widest row's column count.
+* @throws ArchiveError when a cell names a shared string the workbook lacks or a date cell holds no number.
+*/
+function readRows(xml, strings, dates, date1904) {
+	const rows = /* @__PURE__ */ new Map();
+	let width = 0;
+	let next = 1;
+	for (const row of xml.matchAll(/<row(?=[\s>])([^>]*?)(?:\/>|>([\s\S]*?)<\/row>)/g)) {
+		const number = Number(attributesOf(row[1] ?? "")["r"] ?? next);
+		next = number + 1;
+		const cells = [];
+		for (const cell of (row[2] ?? "").matchAll(/<c(?=[\s>])([^>]*?)(?:\/>|>([\s\S]*?)<\/c>)/g)) {
+			const attributes = attributesOf(cell[1] ?? "");
+			const column = attributes["r"] === void 0 ? cells.length : columnOf(attributes["r"]);
+			const body = cell[2] ?? "";
+			const value = /<v(?:\s[^>]*)?>([\s\S]*?)<\/v>/.exec(body)?.[1];
+			let text;
+			if (attributes["t"] === "inlineStr") text = [...body.matchAll(/<t(?:\s[^>]*)?>([\s\S]*?)<\/t>/g)].map((run) => unescape(run[1] ?? "")).join("");
+			else if (value === void 0) text = void 0;
+			else if (attributes["t"] === "s") {
+				text = strings[Number(value)];
+				if (text === void 0) throw new ArchiveError(`row ${String(number)} names the shared string ${value}, which the workbook does not have`);
+			} else if (attributes["t"] === "b") text = value === "0" ? "FALSE" : "TRUE";
+			else if (attributes["t"] === "str" || attributes["t"] === "e") text = unescape(value);
+			else if (dates.has(Number(attributes["s"] ?? "0"))) {
+				const serial = Number(value);
+				if (!Number.isFinite(serial) || serial < 0) throw new ArchiveError(`row ${String(number)} has a date cell holding ${value}`);
+				text = isoOf(serial, date1904);
+			} else text = unescape(value);
+			if (text !== void 0 && text !== "") {
+				cells[column] = text;
+				width = Math.max(width, column + 1);
+			}
+		}
+		rows.set(number, cells);
+	}
+	return {
+		rows,
+		width
+	};
+}
+/**
+* Writes one sheet of an xlsx workbook as CSV text, so a recipe reads it with the table parser: one line for every row number from the first to the last (a row the sheet leaves out is an empty line, so the lines above the header are the rows an editor shows), every line the width of the sheet's widest row, a date cell as ISO 8601 text, a boolean as TRUE or FALSE, a number as the text the workbook stores, and a formula as its stored result.
+* @param bytes - The workbook.
+* @param sheet - The sheet's name.
+* @returns The CSV, in UTF-8.
+* @throws ArchiveError when the bytes are not a workbook, the sheet is missing, or a cell cannot be read.
+*/
+function sheetToCsv(bytes, sheet) {
+	let parts;
+	try {
+		const wanted = /* @__PURE__ */ new Set([
+			"xl/workbook.xml",
+			"xl/_rels/workbook.xml.rels",
+			"xl/sharedStrings.xml",
+			"xl/styles.xml"
+		]);
+		parts = unzipSync(bytes, { filter: (file) => wanted.has(file.name) });
+	} catch (error) {
+		throw new ArchiveError(`not a valid workbook: ${error instanceof Error ? error.message : String(error)}`, { cause: error });
+	}
+	const text = (path) => {
+		const part = getOwn(parts, path);
+		return part === void 0 ? void 0 : new TextDecoder("utf-8").decode(part);
+	};
+	const workbook = text("xl/workbook.xml");
+	const rels = text("xl/_rels/workbook.xml.rels");
+	if (workbook === void 0 || rels === void 0) throw new ArchiveError("the file is not an xlsx workbook: it has no xl/workbook.xml with its relationships");
+	const path = sheetPath(workbook, rels, sheet);
+	const sheetBytes = getOwn(unzipSync(bytes, { filter: (file) => file.name === path }), path);
+	if (sheetBytes === void 0) throw new ArchiveError(`the workbook names the sheet ${sheet} in ${path}, which the file does not have`);
+	const strings = text("xl/sharedStrings.xml");
+	const { rows, width } = readRows(new TextDecoder("utf-8").decode(sheetBytes), strings === void 0 ? [] : sharedStrings(strings), dateStyles(text("xl/styles.xml")), /<workbookPr(?=[\s/>])[^>]*date1904="(?:1|true)"/.test(workbook));
+	const last = Math.max(0, ...rows.keys());
+	const lines = [];
+	for (let number = 1; number <= last; number += 1) {
+		const cells = rows.get(number) ?? [];
+		lines.push(Array.from({ length: width }, (_empty, column) => field(cells[column] ?? "")).join(","));
+	}
+	return new TextEncoder().encode(lines.length === 0 ? "" : `${lines.join("\n")}\n`);
+}
+//#endregion
 //#region src/node/archive.ts
 /**
 * Whether an archive member is a macOS resource fork (`__MACOSX/` or an AppleDouble `._` file), which carries Finder metadata rather than data and never matches a selector.
@@ -1059,6 +1308,10 @@ function pick(paths, member) {
 function unpack(bytes, archive) {
 	if (archive.kind === "none") return { bytes };
 	if (archive.kind === "gzip") return { bytes: gunzip(bytes) };
+	if (archive.kind === "xlsx") return {
+		bytes: sheetToCsv(bytes, archive.sheet),
+		member: archive.sheet
+	};
 	if (archive.kind === "zip") {
 		const names = [];
 		unzip(bytes, (file) => {

package/dist-cli/keepset.mjs

@@ -4,7 +4,7 @@ import { KeepsetError, NAME_SEPARATOR, countTarget, getDataset, listDatasets, li
 import { fetchDataset, roundTripDataset } from "keepset/node";
 import { parseArgs } from "node:util";
 //#region package.json
-var version = "0.19.0";
+var version = "0.20.0";
 const usage = `Usage: keepset <command> [options]
 
 Commands:

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "keepset",
   "description": "Library, CLI and statically generated catalogue for dataset fetch-and-normalise recipes",
-  "version": "0.19.0",
+  "version": "0.20.0",
   "bin": {
     "keepset": "./dist-cli/keepset.mjs"
   },

package/schemas/entry.schema.json

@@ -1 +1 @@
-{"$defs":{"Crosswalk":{"$ref":"https://cdn.jsdelivr.net/npm/twindex@0.1.4/schemas/twindex.schema.json"},"Entry":{"additionalProperties":false,"properties":{"aliases":{"items":{"pattern":"^[A-Za-z0-9][A-Za-z0-9._-]*(?:\\/[A-Za-z0-9][A-Za-z0-9._-]*)*$","type":"string"},"minItems":1,"type":"array"},"category":{"enum":["graph/v1","or/v1"],"type":"string"},"citations":{"items":{"additionalProperties":false,"properties":{"doi":{"pattern":"^10\\.\\d{4,9}\\/\\S+$","type":"string"},"text":{"minLength":1,"type":"string"},"url":{"format":"uri","type":"string"}},"required":["text"],"type":"object"},"type":"array"},"crosswalk":{"anyOf":[{"$ref":"#/$defs/Crosswalk"},{"additionalProperties":false,"properties":{"file":{"type":"string"}},"required":["file"],"type":"object"}]},"description":{"minLength":1,"type":"string"},"domain":{"minLength":1,"type":"string"},"expectedCounts":{"additionalProperties":{"maximum":9007199254740991,"minimum":0,"type":"integer"},"propertyNames":{"pattern":"^[A-Za-z][A-Za-z0-9]*$","type":"string"},"type":"object"},"id":{"pattern":"^[A-Za-z0-9][A-Za-z0-9._-]*$","type":"string"},"licence":{"oneOf":[{"additionalProperties":false,"properties":{"id":{"pattern":"^[A-Za-z0-9][A-Za-z0-9.+-]*$","type":"string"},"kind":{"const":"spdx","type":"string"}},"required":["kind","id"],"type":"object"},{"additionalProperties":false,"properties":{"kind":{"const":"custom","type":"string"},"name":{"minLength":1,"type":"string"},"url":{"format":"uri","type":"string"}},"required":["kind","name","url"],"type":"object"},{"additionalProperties":false,"properties":{"kind":{"const":"unrecorded","type":"string"}},"required":["kind"],"type":"object"}]},"name":{"minLength":1,"type":"string"},"namespace":{"items":{"pattern":"^[A-Za-z0-9][A-Za-z0-9._-]*$","type":"string"},"minItems":1,"type":"array"},"properties":{"additionalProperties":{"type":["string","number","boolean","null"]},"propertyNames":{"pattern":"^[A-Za-z][A-Za-z0-9]*$","type":"string"},"type":"object"},"recipe":{"oneOf":[{"additionalProperties":false,"properties":{"archive":{"oneOf":[{"additionalProperties":false,"properties":{"kind":{"const":"none","type":"string"}},"required":["kind"],"type":"object"},{"additionalProperties":false,"properties":{"kind":{"const":"gzip","type":"string"}},"required":["kind"],"type":"object"},{"additionalProperties":false,"properties":{"kind":{"const":"zip","type":"string"},"member":{"anyOf":[{"additionalProperties":false,"properties":{"path":{"type":"string"}},"required":["path"],"type":"object"},{"additionalProperties":false,"properties":{"extensions":{"items":{"pattern":"^\\.[A-Za-z0-9][A-Za-z0-9.]*$","type":"string"},"minItems":1,"type":"array"}},"required":["extensions"],"type":"object"}]}},"required":["kind","member"],"type":"object"},{"additionalProperties":false,"properties":{"kind":{"const":"tar","type":"string"},"member":{"anyOf":[{"additionalProperties":false,"properties":{"path":{"type":"string"}},"required":["path"],"type":"object"},{"additionalProperties":false,"properties":{"extensions":{"items":{"pattern":"^\\.[A-Za-z0-9][A-Za-z0-9.]*$","type":"string"},"minItems":1,"type":"array"}},"required":["extensions"],"type":"object"}]}},"required":["kind","member"],"type":"object"},{"additionalProperties":false,"properties":{"kind":{"const":"tar.gz","type":"string"},"member":{"anyOf":[{"additionalProperties":false,"properties":{"path":{"type":"string"}},"required":["path"],"type":"object"},{"additionalProperties":false,"properties":{"extensions":{"items":{"pattern":"^\\.[A-Za-z0-9][A-Za-z0-9.]*$","type":"string"},"minItems":1,"type":"array"}},"required":["extensions"],"type":"object"}]}},"required":["kind","member"],"type":"object"}]},"paging":{"oneOf":[{"additionalProperties":false,"properties":{"kind":{"const":"arcgis-query","type":"string"},"orderBy":{"pattern":"^[A-Za-z_][A-Za-z0-9_]*$","type":"string"}},"required":["kind","orderBy"],"type":"object"}]},"parser":{"oneOf":[{"additionalProperties":false,"properties":{"commentPrefixes":{"items":{"minLength":1,"type":"string"},"type":"array"},"delimiter":{"enum":["detect","whitespace","tab","comma","space"],"type":"string"},"encoding":{"enum":["utf-8","latin1"],"type":"string"},"format":{"const":"edge-list","type":"string"},"skipLines":{"maximum":9007199254740991,"minimum":0,"type":"integer"},"sourceColumn":{"maximum":9007199254740991,"minimum":0,"type":"integer"},"targetColumn":{"maximum":9007199254740991,"minimum":0,"type":"integer"}},"required":["format","encoding","delimiter","skipLines","commentPrefixes","sourceColumn","targetColumn"],"type":"object"},{"additionalProperties":false,"properties":{"encoding":{"enum":["utf-8","latin1"],"type":"string"},"format":{"const":"matrix-market","type":"string"}},"required":["format","encoding"],"type":"object"},{"additionalProperties":false,"properties":{"encoding":{"enum":["utf-8","latin1"],"type":"string"},"format":{"const":"gml","type":"string"}},"required":["format","encoding"],"type":"object"},{"additionalProperties":false,"properties":{"encoding":{"enum":["utf-8","latin1"],"type":"string"},"format":{"const":"pajek","type":"string"}},"required":["format","encoding"],"type":"object"},{"additionalProperties":false,"properties":{"columns":{"items":{"pattern":"^[A-Za-z](?:[A-Za-z0-9_]*[A-Za-z0-9])?$","type":"string"},"type":"array"},"delimiter":{"enum":["comma","tab","semicolon"],"type":"string"},"encoding":{"enum":["utf-8","latin1"],"type":"string"},"format":{"const":"csv-table","type":"string"},"idColumn":{"anyOf":[{"pattern":"^[A-Za-z](?:[A-Za-z0-9_]*[A-Za-z0-9])?$","type":"string"},{"type":"null"}]},"numericColumns":{"items":{"additionalProperties":false,"properties":{"column":{"pattern":"^[A-Za-z](?:[A-Za-z0-9_]*[A-Za-z0-9])?$","type":"string"},"factor":{"exclusiveMinimum":0,"type":"number"}},"required":["column","factor"],"type":"object"},"type":"array"},"skipLines":{"maximum":9007199254740991,"minimum":0,"type":"integer"}},"required":["format","encoding","delimiter","skipLines","idColumn","numericColumns"],"type":"object"},{"additionalProperties":false,"properties":{"columns":{"items":{"pattern":"^[A-Za-z](?:[A-Za-z0-9_]*[A-Za-z0-9])?$","type":"string"},"minItems":1,"type":"array"},"dateColumns":{"items":{"pattern":"^[A-Za-z](?:[A-Za-z0-9_]*[A-Za-z0-9])?$","type":"string"},"type":"array"},"encoding":{"const":"utf-8","type":"string"},"format":{"const":"geojson","type":"string"},"idColumn":{"anyOf":[{"pattern":"^[A-Za-z](?:[A-Za-z0-9_]*[A-Za-z0-9])?$","type":"string"},{"type":"null"}]},"numericColumns":{"items":{"additionalProperties":false,"properties":{"column":{"pattern":"^[A-Za-z](?:[A-Za-z0-9_]*[A-Za-z0-9])?$","type":"string"},"factor":{"exclusiveMinimum":0,"type":"number"}},"required":["column","factor"],"type":"object"},"type":"array"}},"required":["format","encoding","idColumn","numericColumns","dateColumns","columns"],"type":"object"}]},"source":{"maximum":9007199254740991,"minimum":0,"type":"integer"},"status":{"const":"fetchable","type":"string"}},"required":["status","source","archive","parser"],"type":"object"},{"additionalProperties":false,"properties":{"reason":{"minLength":1,"type":"string"},"status":{"const":"not-fetchable","type":"string"}},"required":["status","reason"],"type":"object"}]},"sources":{"items":{"additionalProperties":false,"properties":{"retrieved":{"format":"date","pattern":"^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))$","type":"string"},"snapshot":{"additionalProperties":false,"properties":{"timestamp":{"pattern":"^\\d{8}(?:\\d{6})?$","type":"string"},"url":{"format":"uri","type":"string"}},"required":["url","timestamp"],"type":"object"},"status":{"enum":["live","dead"],"type":"string"},"url":{"format":"uri","type":"string"}},"required":["url","retrieved","status"],"type":"object"},"minItems":1,"type":"array"},"tags":{"items":{"minLength":1,"type":"string"},"type":"array"}},"required":["id","name","tags","category","sources","licence","citations","recipe","crosswalk","expectedCounts","properties"],"type":"object"}},"$id":"https://cdn.jsdelivr.net/npm/keepset@0.19.0/schemas/entry.schema.json","$ref":"#/$defs/Entry","$schema":"https://json-schema.org/draft/2020-12/schema"}
+{"$defs":{"Crosswalk":{"$ref":"https://cdn.jsdelivr.net/npm/twindex@0.1.4/schemas/twindex.schema.json"},"Entry":{"additionalProperties":false,"properties":{"aliases":{"items":{"pattern":"^[A-Za-z0-9][A-Za-z0-9._-]*(?:\\/[A-Za-z0-9][A-Za-z0-9._-]*)*$","type":"string"},"minItems":1,"type":"array"},"category":{"enum":["graph/v1","or/v1"],"type":"string"},"citations":{"items":{"additionalProperties":false,"properties":{"doi":{"pattern":"^10\\.\\d{4,9}\\/\\S+$","type":"string"},"text":{"minLength":1,"type":"string"},"url":{"format":"uri","type":"string"}},"required":["text"],"type":"object"},"type":"array"},"crosswalk":{"anyOf":[{"$ref":"#/$defs/Crosswalk"},{"additionalProperties":false,"properties":{"file":{"type":"string"}},"required":["file"],"type":"object"}]},"description":{"minLength":1,"type":"string"},"domain":{"minLength":1,"type":"string"},"expectedCounts":{"additionalProperties":{"maximum":9007199254740991,"minimum":0,"type":"integer"},"propertyNames":{"pattern":"^[A-Za-z][A-Za-z0-9]*$","type":"string"},"type":"object"},"id":{"pattern":"^[A-Za-z0-9][A-Za-z0-9._-]*$","type":"string"},"licence":{"oneOf":[{"additionalProperties":false,"properties":{"id":{"pattern":"^[A-Za-z0-9][A-Za-z0-9.+-]*$","type":"string"},"kind":{"const":"spdx","type":"string"}},"required":["kind","id"],"type":"object"},{"additionalProperties":false,"properties":{"kind":{"const":"custom","type":"string"},"name":{"minLength":1,"type":"string"},"url":{"format":"uri","type":"string"}},"required":["kind","name","url"],"type":"object"},{"additionalProperties":false,"properties":{"kind":{"const":"unrecorded","type":"string"}},"required":["kind"],"type":"object"}]},"name":{"minLength":1,"type":"string"},"namespace":{"items":{"pattern":"^[A-Za-z0-9][A-Za-z0-9._-]*$","type":"string"},"minItems":1,"type":"array"},"properties":{"additionalProperties":{"type":["string","number","boolean","null"]},"propertyNames":{"pattern":"^[A-Za-z][A-Za-z0-9]*$","type":"string"},"type":"object"},"recipe":{"oneOf":[{"additionalProperties":false,"properties":{"archive":{"oneOf":[{"additionalProperties":false,"properties":{"kind":{"const":"none","type":"string"}},"required":["kind"],"type":"object"},{"additionalProperties":false,"properties":{"kind":{"const":"gzip","type":"string"}},"required":["kind"],"type":"object"},{"additionalProperties":false,"properties":{"kind":{"const":"zip","type":"string"},"member":{"anyOf":[{"additionalProperties":false,"properties":{"path":{"type":"string"}},"required":["path"],"type":"object"},{"additionalProperties":false,"properties":{"extensions":{"items":{"pattern":"^\\.[A-Za-z0-9][A-Za-z0-9.]*$","type":"string"},"minItems":1,"type":"array"}},"required":["extensions"],"type":"object"}]}},"required":["kind","member"],"type":"object"},{"additionalProperties":false,"properties":{"kind":{"const":"tar","type":"string"},"member":{"anyOf":[{"additionalProperties":false,"properties":{"path":{"type":"string"}},"required":["path"],"type":"object"},{"additionalProperties":false,"properties":{"extensions":{"items":{"pattern":"^\\.[A-Za-z0-9][A-Za-z0-9.]*$","type":"string"},"minItems":1,"type":"array"}},"required":["extensions"],"type":"object"}]}},"required":["kind","member"],"type":"object"},{"additionalProperties":false,"properties":{"kind":{"const":"tar.gz","type":"string"},"member":{"anyOf":[{"additionalProperties":false,"properties":{"path":{"type":"string"}},"required":["path"],"type":"object"},{"additionalProperties":false,"properties":{"extensions":{"items":{"pattern":"^\\.[A-Za-z0-9][A-Za-z0-9.]*$","type":"string"},"minItems":1,"type":"array"}},"required":["extensions"],"type":"object"}]}},"required":["kind","member"],"type":"object"},{"additionalProperties":false,"properties":{"kind":{"const":"xlsx","type":"string"},"sheet":{"minLength":1,"type":"string"}},"required":["kind","sheet"],"type":"object"}]},"paging":{"oneOf":[{"additionalProperties":false,"properties":{"kind":{"const":"arcgis-query","type":"string"},"orderBy":{"pattern":"^[A-Za-z_][A-Za-z0-9_]*$","type":"string"}},"required":["kind","orderBy"],"type":"object"}]},"parser":{"oneOf":[{"additionalProperties":false,"properties":{"commentPrefixes":{"items":{"minLength":1,"type":"string"},"type":"array"},"delimiter":{"enum":["detect","whitespace","tab","comma","space"],"type":"string"},"encoding":{"enum":["utf-8","latin1"],"type":"string"},"format":{"const":"edge-list","type":"string"},"skipLines":{"maximum":9007199254740991,"minimum":0,"type":"integer"},"sourceColumn":{"maximum":9007199254740991,"minimum":0,"type":"integer"},"targetColumn":{"maximum":9007199254740991,"minimum":0,"type":"integer"}},"required":["format","encoding","delimiter","skipLines","commentPrefixes","sourceColumn","targetColumn"],"type":"object"},{"additionalProperties":false,"properties":{"encoding":{"enum":["utf-8","latin1"],"type":"string"},"format":{"const":"matrix-market","type":"string"}},"required":["format","encoding"],"type":"object"},{"additionalProperties":false,"properties":{"encoding":{"enum":["utf-8","latin1"],"type":"string"},"format":{"const":"gml","type":"string"}},"required":["format","encoding"],"type":"object"},{"additionalProperties":false,"properties":{"encoding":{"enum":["utf-8","latin1"],"type":"string"},"format":{"const":"pajek","type":"string"}},"required":["format","encoding"],"type":"object"},{"additionalProperties":false,"properties":{"columns":{"items":{"pattern":"^[A-Za-z](?:[A-Za-z0-9_]*[A-Za-z0-9])?$","type":"string"},"type":"array"},"delimiter":{"enum":["comma","tab","semicolon"],"type":"string"},"encoding":{"enum":["utf-8","latin1"],"type":"string"},"format":{"const":"csv-table","type":"string"},"idColumn":{"anyOf":[{"pattern":"^[A-Za-z](?:[A-Za-z0-9_]*[A-Za-z0-9])?$","type":"string"},{"type":"null"}]},"numericColumns":{"items":{"additionalProperties":false,"properties":{"column":{"pattern":"^[A-Za-z](?:[A-Za-z0-9_]*[A-Za-z0-9])?$","type":"string"},"factor":{"exclusiveMinimum":0,"type":"number"}},"required":["column","factor"],"type":"object"},"type":"array"},"skipLines":{"maximum":9007199254740991,"minimum":0,"type":"integer"}},"required":["format","encoding","delimiter","skipLines","idColumn","numericColumns"],"type":"object"},{"additionalProperties":false,"properties":{"columns":{"items":{"pattern":"^[A-Za-z](?:[A-Za-z0-9_]*[A-Za-z0-9])?$","type":"string"},"minItems":1,"type":"array"},"dateColumns":{"items":{"pattern":"^[A-Za-z](?:[A-Za-z0-9_]*[A-Za-z0-9])?$","type":"string"},"type":"array"},"encoding":{"const":"utf-8","type":"string"},"format":{"const":"geojson","type":"string"},"idColumn":{"anyOf":[{"pattern":"^[A-Za-z](?:[A-Za-z0-9_]*[A-Za-z0-9])?$","type":"string"},{"type":"null"}]},"numericColumns":{"items":{"additionalProperties":false,"properties":{"column":{"pattern":"^[A-Za-z](?:[A-Za-z0-9_]*[A-Za-z0-9])?$","type":"string"},"factor":{"exclusiveMinimum":0,"type":"number"}},"required":["column","factor"],"type":"object"},"type":"array"}},"required":["format","encoding","idColumn","numericColumns","dateColumns","columns"],"type":"object"}]},"source":{"maximum":9007199254740991,"minimum":0,"type":"integer"},"status":{"const":"fetchable","type":"string"}},"required":["status","source","archive","parser"],"type":"object"},{"additionalProperties":false,"properties":{"reason":{"minLength":1,"type":"string"},"status":{"const":"not-fetchable","type":"string"}},"required":["status","reason"],"type":"object"}]},"sources":{"items":{"additionalProperties":false,"properties":{"retrieved":{"format":"date","pattern":"^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))$","type":"string"},"snapshot":{"additionalProperties":false,"properties":{"timestamp":{"pattern":"^\\d{8}(?:\\d{6})?$","type":"string"},"url":{"format":"uri","type":"string"}},"required":["url","timestamp"],"type":"object"},"status":{"enum":["live","dead"],"type":"string"},"url":{"format":"uri","type":"string"}},"required":["url","retrieved","status"],"type":"object"},"minItems":1,"type":"array"},"tags":{"items":{"minLength":1,"type":"string"},"type":"array"}},"required":["id","name","tags","category","sources","licence","citations","recipe","crosswalk","expectedCounts","properties"],"type":"object"}},"$id":"https://cdn.jsdelivr.net/npm/keepset@0.20.0/schemas/entry.schema.json","$ref":"#/$defs/Entry","$schema":"https://json-schema.org/draft/2020-12/schema"}

package/schemas/manifest.schema.json

@@ -1 +1 @@
-{"$defs":{"Manifest":{"additionalProperties":false,"properties":{"description":{"minLength":1,"type":"string"},"id":{"pattern":"^[A-Za-z0-9][A-Za-z0-9._-]*$","type":"string"},"lineage":{"additionalProperties":false,"properties":{"catalogue":{"pattern":"^[A-Za-z0-9][A-Za-z0-9._-]*$","type":"string"},"repository":{"format":"uri","type":"string"},"version":{"pattern":"^(?:0|[1-9]\\d*)\\.(?:0|[1-9]\\d*)\\.(?:0|[1-9]\\d*)(?:-[0-9A-Za-z-]+(?:\\.[0-9A-Za-z-]+)*)?(?:\\+[0-9A-Za-z-]+(?:\\.[0-9A-Za-z-]+)*)?$","type":"string"}},"required":["catalogue","version","repository"],"type":"object"},"name":{"minLength":1,"type":"string"},"namespaceAliases":{"additionalProperties":{"items":{"pattern":"^[A-Za-z0-9][A-Za-z0-9._-]*$","type":"string"},"minItems":1,"type":"array"},"propertyNames":{"pattern":"^[A-Za-z0-9][A-Za-z0-9._-]*$","type":"string"},"type":"object"},"repository":{"format":"uri","type":"string"},"version":{"pattern":"^(?:0|[1-9]\\d*)\\.(?:0|[1-9]\\d*)\\.(?:0|[1-9]\\d*)(?:-[0-9A-Za-z-]+(?:\\.[0-9A-Za-z-]+)*)?(?:\\+[0-9A-Za-z-]+(?:\\.[0-9A-Za-z-]+)*)?$","type":"string"}},"required":["id","name","description","version","repository"],"type":"object"}},"$id":"https://cdn.jsdelivr.net/npm/keepset@0.19.0/schemas/manifest.schema.json","$ref":"#/$defs/Manifest","$schema":"https://json-schema.org/draft/2020-12/schema"}
+{"$defs":{"Manifest":{"additionalProperties":false,"properties":{"description":{"minLength":1,"type":"string"},"id":{"pattern":"^[A-Za-z0-9][A-Za-z0-9._-]*$","type":"string"},"lineage":{"additionalProperties":false,"properties":{"catalogue":{"pattern":"^[A-Za-z0-9][A-Za-z0-9._-]*$","type":"string"},"repository":{"format":"uri","type":"string"},"version":{"pattern":"^(?:0|[1-9]\\d*)\\.(?:0|[1-9]\\d*)\\.(?:0|[1-9]\\d*)(?:-[0-9A-Za-z-]+(?:\\.[0-9A-Za-z-]+)*)?(?:\\+[0-9A-Za-z-]+(?:\\.[0-9A-Za-z-]+)*)?$","type":"string"}},"required":["catalogue","version","repository"],"type":"object"},"name":{"minLength":1,"type":"string"},"namespaceAliases":{"additionalProperties":{"items":{"pattern":"^[A-Za-z0-9][A-Za-z0-9._-]*$","type":"string"},"minItems":1,"type":"array"},"propertyNames":{"pattern":"^[A-Za-z0-9][A-Za-z0-9._-]*$","type":"string"},"type":"object"},"repository":{"format":"uri","type":"string"},"version":{"pattern":"^(?:0|[1-9]\\d*)\\.(?:0|[1-9]\\d*)\\.(?:0|[1-9]\\d*)(?:-[0-9A-Za-z-]+(?:\\.[0-9A-Za-z-]+)*)?(?:\\+[0-9A-Za-z-]+(?:\\.[0-9A-Za-z-]+)*)?$","type":"string"}},"required":["id","name","description","version","repository"],"type":"object"}},"$id":"https://cdn.jsdelivr.net/npm/keepset@0.20.0/schemas/manifest.schema.json","$ref":"#/$defs/Manifest","$schema":"https://json-schema.org/draft/2020-12/schema"}