keepset 0.22.0 → 0.23.0

package/README.md

@@ -63,7 +63,7 @@ The catalogue itself is a manifest (`catalogue/manifest.json`: id, version, repo
 
 ## Categories and normalisation targets
 
-A category names a normalisation target: the shape every entry in that category resolves to, whatever its native shape. `graph/v1` is `{ meta, nodes, edges }` with unique node ids and edges whose endpoints name nodes; its entries are graph datasets taken from upstream collections such as SuiteSparse, Netzschleuder, SNAP, KONECT and OGB. `or/v1` is `{ meta, nodes }`, an operations-research instance as the nodes it offers to visit, each flat with optional coordinates, prize, prize probability, duration, travel time, skill, territory, lifecycle status and times, and deadline, read from tabular sources by the `csv-table` parser. Its entries come from a survey of open operations-research datasets, imported with a curation that records, for each source, what its download gives and how its columns map onto the node; a dataset whose source has no usable table is imported without a recipe and says why. A new category starts by defining its target schema in `src/targets/` and registering it in the category registry; an entry cannot name a category that does not exist. The statically generated site renders every entry with schema.org Dataset JSON-LD, so the catalogue surfaces in the dataset discovery layers.
+A category names a normalisation target: the shape every entry in that category resolves to, whatever its native shape. `graph/v1` is `{ meta, nodes, edges }` with unique node ids and edges whose endpoints name nodes; its entries are graph datasets taken from upstream collections such as SuiteSparse, Netzschleuder, SNAP, KONECT and OGB. `or/v1` is `{ meta, nodes }`, an operations-research instance as the nodes it offers to visit, each flat with optional coordinates, prize, prize probability, duration, travel time, skill, territory, lifecycle status and times, and deadline, read from tabular sources by the `csv-table` parser (a delimited file, a member of an archive, a sheet of an Excel workbook, or an open data portal read a page at a time) and from ArcGIS feature layers by the `geojson` parser. Its entries come from a survey of open operations-research datasets, imported with a curation that records, for each source, what its download gives and how its columns map onto the node; a dataset whose source has no usable table is imported without a recipe and says why. A new category starts by defining its target schema in `src/targets/` and registering it in the category registry; an entry cannot name a category that does not exist. The statically generated site renders every entry with schema.org Dataset JSON-LD, so the catalogue surfaces in the dataset discovery layers.
 
 ## Licensing
 

package/dist/{bundled-CAsUNCDb.js → bundled-BKl0C7kF.js}

@@ -516,7 +516,7 @@ const ParserSchema = z.discriminatedUnion("format", [
 		path: ["dateColumns"]
 	})
 ]);
-/** Where a source is a paged query and not one file. An ArcGIS feature layer returns a limited number of features per request: the source URL is the layer's, the download reads every page in `orderBy` order and the parser reads the one GeoJSON collection they make. A Socrata resource endpoint (`/resource/<id>.csv`) is read `pageSize` rows at a time in the order of its row ids, and a CKAN datastore dump (`/datastore/dump/<id>`) `pageSize` rows at a time, each page a CSV with its own header; the download joins them into the one CSV the parser reads, so no single response has to survive a long transfer. */
+/** Where a source is a paged query and not one file. An ArcGIS feature layer returns a limited number of features per request: the source URL is the layer's, the download reads every page in `orderBy` order and the parser reads the one GeoJSON collection they make. A Socrata resource endpoint (`/resource/<id>.csv`) is read `pageSize` rows at a time in the order of its row ids, a CKAN datastore dump (`/datastore/dump/<id>`) and an OpenFEMA entity (`/api/open/v<n>/<Entity>`, with any `$select` or `$filter` in the source URL) `pageSize` rows at a time, each page a CSV with its own header; the download joins them into the one CSV the parser reads, so no single response has to survive a long transfer. */
 const PagingSchema = z.discriminatedUnion("kind", [
 	z.object({
 		kind: z.literal("arcgis-query"),
@@ -529,6 +529,10 @@ const PagingSchema = z.discriminatedUnion("kind", [
 	z.object({
 		kind: z.literal("ckan-datastore"),
 		pageSize: z.int().min(1)
+	}).strict(),
+	z.object({
+		kind: z.literal("openfema"),
+		pageSize: z.int().min(1)
 	}).strict()
 ]);
 /** How to obtain the dataset: a fetchable recipe naming the source (by index into `sources`), the archive layout and the parser, or a statement that no declarative recipe exists yet and why. */
@@ -905,7 +909,7 @@ 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": "1.10.0",
+		"version": "1.11.0",
 		"repository": "https://github.com/Mearman/keepset",
 		"namespaceAliases": {
 			"networkrepository": ["nr"],
@@ -6414,14 +6418,90 @@ var catalogue_default = {
 				"url": "https://www.fema.gov/openfema-data-page/fima-nfip-redacted-claims-v2",
 				"retrieved": "2026-10-19",
 				"status": "live"
+			}, {
+				"url": "https://www.fema.gov/api/open/v3/NfipClaims?$select=id,openDate,latitude,longitude,amountPaidOnBuildingClaim",
+				"retrieved": "2026-10-19",
+				"status": "live"
 			}],
-			"licence": { "kind": "unrecorded" },
+			"licence": {
+				"kind": "custom",
+				"name": "OpenFEMA Terms and Conditions",
+				"url": "https://www.fema.gov/about/openfema/terms-conditions"
+			},
 			"citations": [],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "The OpenFEMA v3 API pages claims anonymously as CSV, but the table has millions of rows whose locations are rounded to a tenth of a degree, the terms of use limit it to statistical use without reidentification, and keepset has no recipe paging for this API."
+				"status": "fetchable",
+				"source": 1,
+				"paging": {
+					"kind": "openfema",
+					"pageSize": 5e4
+				},
+				"archive": { "kind": "none" },
+				"parser": {
+					"format": "csv-table",
+					"encoding": "utf-8",
+					"delimiter": "comma",
+					"skipLines": 0,
+					"idColumn": "id",
+					"numericColumns": [
+						{
+							"column": "latitude",
+							"factor": 1
+						},
+						{
+							"column": "longitude",
+							"factor": 1
+						},
+						{
+							"column": "amountPaidOnBuildingClaim",
+							"factor": 1
+						}
+					],
+					"columns": [
+						"latitude",
+						"longitude",
+						"openDate",
+						"amountPaidOnBuildingClaim"
+					]
+				}
+			},
+			"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[].latitude",
+						"to": "nodes[].lat"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].longitude",
+						"to": "nodes[].lon"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].openDate",
+						"to": "nodes[].opened"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].amountPaidOnBuildingClaim",
+						"to": "nodes[].prize"
+					}
+				],
+				"oneWay": []
 			},
-			"crosswalk": { "file": "crosswalks/or-v1/nodes.json" },
 			"expectedCounts": {},
 			"properties": { "surveyId": "or-122" }
 		},

package/dist/{categories-CJZ2LiJh.d.ts → categories-BGjPWXpS.d.ts}

@@ -183,6 +183,9 @@ declare const RecipeSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
   }, z.core.$strict>, z.ZodObject<{
     kind: z.ZodLiteral<"ckan-datastore">;
     pageSize: z.ZodInt;
+  }, z.core.$strict>, z.ZodObject<{
+    kind: z.ZodLiteral<"openfema">;
+    pageSize: z.ZodInt;
   }, z.core.$strict>], "kind">>;
   archive: z.ZodDiscriminatedUnion<[z.ZodObject<{
     kind: z.ZodLiteral<"none">;
@@ -346,6 +349,9 @@ declare const EntrySchema: z.ZodObject<{
     }, z.core.$strict>, z.ZodObject<{
       kind: z.ZodLiteral<"ckan-datastore">;
       pageSize: z.ZodInt;
+    }, z.core.$strict>, z.ZodObject<{
+      kind: z.ZodLiteral<"openfema">;
+      pageSize: z.ZodInt;
     }, z.core.$strict>], "kind">>;
     archive: z.ZodDiscriminatedUnion<[z.ZodObject<{
       kind: z.ZodLiteral<"none">;
@@ -563,6 +569,9 @@ declare const EntrySchema: z.ZodObject<{
       } | {
         kind: "ckan-datastore";
         pageSize: number;
+      } | {
+        kind: "openfema";
+        pageSize: number;
       } | undefined;
     } | {
       status: "not-fetchable";
@@ -723,6 +732,9 @@ declare const CatalogueIndexSchema: z.ZodObject<{
       }, z.core.$strict>, z.ZodObject<{
         kind: z.ZodLiteral<"ckan-datastore">;
         pageSize: z.ZodInt;
+      }, z.core.$strict>, z.ZodObject<{
+        kind: z.ZodLiteral<"openfema">;
+        pageSize: z.ZodInt;
       }, z.core.$strict>], "kind">>;
       archive: z.ZodDiscriminatedUnion<[z.ZodObject<{
         kind: z.ZodLiteral<"none">;
@@ -940,6 +952,9 @@ declare const CatalogueIndexSchema: z.ZodObject<{
         } | {
           kind: "ckan-datastore";
           pageSize: number;
+        } | {
+          kind: "openfema";
+          pageSize: number;
         } | undefined;
       } | {
         status: "not-fetchable";
@@ -1082,6 +1097,9 @@ declare const CatalogueIndexSchema: z.ZodObject<{
         } | {
           kind: "ckan-datastore";
           pageSize: number;
+        } | {
+          kind: "openfema";
+          pageSize: number;
         } | undefined;
       } | {
         status: "not-fetchable";

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-CJZ2LiJh.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-BGjPWXpS.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-CAsUNCDb.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-BKl0C7kF.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-CJZ2LiJh.js";
+import { G as Entry, T as Dataset, at as Snapshot, i as CategoryTarget, st as Source } from "../categories-BGjPWXpS.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-CAsUNCDb.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-BKl0C7kF.js";
 import { RoundTripMismatchError, assertRoundTrip, encode } from "twindex";
 import { z } from "zod";
 import { createHash } from "node:crypto";
@@ -1682,6 +1682,56 @@ async function downloadCkanDatastore(dump, pageSize, port, signal) {
 		signal
 	});
 }
+const OpenFemaCountSchema = z.object({ metadata: z.object({ count: z.int().min(0) }) });
+/**
+* Downloads a whole OpenFEMA entity, or the rows of it the source URL selects, as one CSV: the row count is read from the API's own metadata, then pages of `pageSize` rows in the order of the entity's id, each checked to hold the rows it should, and joined under the first page's header.
+* @param entity - The entity's URL with any `$select` or `$filter` but no `$top`, `$skip`, `$orderby` or `$format`, such as `https://www.fema.gov/api/open/v3/NfipClaims?$select=id,state`.
+* @param pageSize - How many rows a page holds.
+* @param port - The network port.
+* @param signal - Aborts the download.
+* @returns The bytes of one CSV, which is what the parser reads and what the provenance hashes.
+* @throws KeepsetError when the source URL sets a paging parameter, the entity does not report a count, or a page is not what it should be.
+*/
+async function downloadOpenFema(entity, pageSize, port, signal) {
+	const base = new URL(entity);
+	for (const name of [
+		"$top",
+		"$skip",
+		"$orderby",
+		"$format",
+		"$inlinecount"
+	]) if (base.searchParams.has(name)) throw new KeepsetError(`${entity} sets ${name}, which the download sets itself`);
+	const withParameters = (parameters) => {
+		const url = new URL(entity);
+		for (const [name, value] of Object.entries(parameters)) url.searchParams.set(name, value);
+		return url.href;
+	};
+	const countUrl = withParameters({
+		$inlinecount: "allpages",
+		$top: "1"
+	});
+	let body;
+	try {
+		body = JSON.parse(new TextDecoder("utf-8").decode(await withAttempts(async () => getBytes(port, countUrl, signal), signal)));
+	} catch (error) {
+		throw new KeepsetError(`${countUrl} did not answer JSON (${error instanceof Error ? error.message : String(error)})`);
+	}
+	const count = OpenFemaCountSchema.safeParse(body);
+	if (!count.success) throw new KeepsetError(`${entity} did not report a row count`);
+	return downloadPages({
+		resource: entity,
+		pageUrl: (offset) => withParameters({
+			$format: "csv",
+			$orderby: "id",
+			$top: String(pageSize),
+			$skip: String(offset)
+		}),
+		pageSize,
+		count: count.data.metadata.count,
+		port,
+		signal
+	});
+}
 /**
 * Downloads a paged source as the one file its pages make, in the way its recipe's paging says.
 * @param url - The source's URL.
@@ -1693,7 +1743,8 @@ async function downloadCkanDatastore(dump, pageSize, port, signal) {
 */
 async function downloadPaged(url, paging, port, signal) {
 	if (paging.kind === "arcgis-query") return downloadArcgisLayer(url, paging.orderBy, port, signal);
-	return paging.kind === "socrata-resource" ? downloadSocrataResource(url, paging.pageSize, port, signal) : downloadCkanDatastore(url, paging.pageSize, port, signal);
+	if (paging.kind === "socrata-resource") return downloadSocrataResource(url, paging.pageSize, port, signal);
+	return paging.kind === "ckan-datastore" ? downloadCkanDatastore(url, paging.pageSize, port, signal) : downloadOpenFema(url, paging.pageSize, port, signal);
 }
 //#endregion
 //#region src/node/fetch-dataset.ts

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 = "0.22.0";
+var version = "0.23.0";
 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": "0.22.0",
+  "version": "0.23.0",
   "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"},{"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_]*$","type":"string"}},"required":["kind","orderBy"],"type":"object"},{"additionalProperties":false,"properties":{"kind":{"const":"socrata-resource","type":"string"},"pageSize":{"maximum":9007199254740991,"minimum":1,"type":"integer"}},"required":["kind","pageSize"],"type":"object"},{"additionalProperties":false,"properties":{"kind":{"const":"ckan-datastore","type":"string"},"pageSize":{"maximum":9007199254740991,"minimum":1,"type":"integer"}},"required":["kind","pageSize"],"type":"object"}]},"parser":{"oneOf":[{"additionalProperties":false,"properties":{"commentPrefixes":{"items":{"minLength":1,"type":"string"},"type":"array"},"delimiter":{"enum":["detect","whitespace","tab","comma","space"],"type":"string"},"encoding":{"enum":["utf-8","latin1"],"type":"string"},"format":{"const":"edge-list","type":"string"},"skipLines":{"maximum":9007199254740991,"minimum":0,"type":"integer"},"sourceColumn":{"maximum":9007199254740991,"minimum":0,"type":"integer"},"targetColumn":{"maximum":9007199254740991,"minimum":0,"type":"integer"}},"required":["format","encoding","delimiter","skipLines","commentPrefixes","sourceColumn","targetColumn"],"type":"object"},{"additionalProperties":false,"properties":{"encoding":{"enum":["utf-8","latin1"],"type":"string"},"format":{"const":"matrix-market","type":"string"}},"required":["format","encoding"],"type":"object"},{"additionalProperties":false,"properties":{"encoding":{"enum":["utf-8","latin1"],"type":"string"},"format":{"const":"gml","type":"string"}},"required":["format","encoding"],"type":"object"},{"additionalProperties":false,"properties":{"encoding":{"enum":["utf-8","latin1"],"type":"string"},"format":{"const":"pajek","type":"string"}},"required":["format","encoding"],"type":"object"},{"additionalProperties":false,"properties":{"columns":{"items":{"pattern":"^[A-Za-z](?:[A-Za-z0-9_]*[A-Za-z0-9])?$","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])?$","type":"string"},{"type":"null"}]},"nullValues":{"items":{"minLength":1,"type":"string"},"type":"array"},"numericColumns":{"items":{"additionalProperties":false,"properties":{"column":{"pattern":"^[A-Za-z](?:[A-Za-z0-9_]*[A-Za-z0-9])?$","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"}},"$id":"https://cdn.jsdelivr.net/npm/keepset@0.22.0/schemas/entry.schema.json","$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"},{"additionalProperties":false,"properties":{"kind":{"const":"socrata-resource","type":"string"},"pageSize":{"maximum":9007199254740991,"minimum":1,"type":"integer"}},"required":["kind","pageSize"],"type":"object"},{"additionalProperties":false,"properties":{"kind":{"const":"ckan-datastore","type":"string"},"pageSize":{"maximum":9007199254740991,"minimum":1,"type":"integer"}},"required":["kind","pageSize"],"type":"object"},{"additionalProperties":false,"properties":{"kind":{"const":"openfema","type":"string"},"pageSize":{"maximum":9007199254740991,"minimum":1,"type":"integer"}},"required":["kind","pageSize"],"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])?$","type":"string"},{"type":"null"}]},"nullValues":{"items":{"minLength":1,"type":"string"},"type":"array"},"numericColumns":{"items":{"additionalProperties":false,"properties":{"column":{"pattern":"^[A-Za-z](?:[A-Za-z0-9_]*[A-Za-z0-9])?$","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"}},"$id":"https://cdn.jsdelivr.net/npm/keepset@0.23.0/schemas/entry.schema.json","$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@0.22.0/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"}},"$id":"https://cdn.jsdelivr.net/npm/keepset@0.23.0/schemas/manifest.schema.json","$ref":"#/$defs/Manifest","$schema":"https://json-schema.org/draft/2020-12/schema"}