keepset 0.33.0 → 0.35.0

package/dist/{bundled-pT7q4sWm.js → bundled-OGg9e42x.js}

@@ -511,22 +511,28 @@ const ArchiveMemberSchema = z.union([
 const FileArchiveKindSchema = z.enum([
 	"zip",
 	"tar",
-	"tar.gz"
+	"tar.gz",
+	"tar.bz2"
 ]);
-/** An archive a collection is read from: every file a selector matches, at least one. */
+/** An archive a collection is read from: every file a selector matches, at least one. With `inner` of kind `xlsx`, every matched member is a workbook and each of its sheets, in the workbook's order, is one file of the collection: the sheet's CSV, at the path of the member and the sheet's name joined by `/`, for an instance format laid out on a sheet. `sheets` is a regular expression a sheet's whole name must match for the sheet to be read (every sheet when it is absent), and it must match at least one sheet of every workbook. */
 const CollectionArchiveSchema = z.object({
 	kind: FileArchiveKindSchema,
-	members: ArchiveMemberSchema
+	members: ArchiveMemberSchema,
+	inner: z.object({
+		kind: z.literal("xlsx"),
+		sheets: MemberPatternSchema.optional()
+	}).strict().optional()
 }).strict();
 /** How a member that is itself an archive unpacks into the file the parser reads: gunzipped, or one member of it selected. It nests one level, which is as deep as any source in the catalogue goes. */
 const InnerArchiveSchema = z.union([z.object({ kind: z.literal("gzip") }).strict(), z.object({
 	kind: FileArchiveKindSchema,
 	member: ArchiveMemberSchema
 }).strict()]);
-/** How the downloaded bytes unpack into the file the parser reads, or for a collection the files it reads one by one. A `members` selector gives every member it matches, at least one, in path order. A member that is an archive in its turn (a contest bundle that ships its problems as a zip inside the zip) is unpacked by `inner`. A workbook (`xlsx`) is read as the CSV of its named sheet, with dates as ISO 8601 text, for the `csv-table` parser. */
+/** How the downloaded bytes unpack into the file the parser reads, or for a collection the files it reads one by one. A `members` selector gives every member it matches, at least one, in path order. `gzip` and `bzip2` are one compressed file, and `tar.gz` and `tar.bz2` a tar archive compressed with them. A member that is an archive in its turn (a contest bundle that ships its problems as a zip inside the zip) is unpacked by `inner`. A workbook (`xlsx`) is read as the CSV of its named sheet, with dates as ISO 8601 text, for the `csv-table` parser. A point shapefile (`shapefile`) is a zip whose `member` selects the `.shp`, read with the `.dbf`, `.prj` and `.cpg` of the same name beside it as the CSV of its attribute table with each point's stored coordinates and its WGS84 position, for the `csv-table` parser. */
 const ArchiveSchema = z.union([
 	z.object({ kind: z.literal("none") }).strict(),
 	z.object({ kind: z.literal("gzip") }).strict(),
+	z.object({ kind: z.literal("bzip2") }).strict(),
 	z.object({
 		kind: FileArchiveKindSchema,
 		member: ArchiveMemberSchema,
@@ -536,6 +542,10 @@ const ArchiveSchema = z.union([
 	z.object({
 		kind: z.literal("xlsx"),
 		sheet: z.string().min(1)
+	}).strict(),
+	z.object({
+		kind: z.literal("shapefile"),
+		member: ArchiveMemberSchema
 	}).strict()
 ]);
 const ColumnSchema = z.int().min(0);
@@ -567,6 +577,30 @@ const ParserSchema = z.discriminatedUnion("format", [
 		format: z.literal("matrix-market"),
 		encoding: EncodingSchema
 	}).strict(),
+	z.object({
+		format: z.literal("user-item-ratings"),
+		encoding: z.literal("utf-8"),
+		/** What separates the fields of a line: a comma, a tab, or the two colons of MovieLens's `ratings.dat`. */
+		delimiter: z.enum([
+			"comma",
+			"tab",
+			"double-colon"
+		]),
+		/** The header lines before the first rating, counted as the file's lines. */
+		skipLines: z.int().min(0),
+		/** What the rated items are, which is their node type and fixes the prefix of their ids. */
+		itemType: z.enum(["movie", "product"]),
+		/** The top of the rating scale: a rating is divided by it to give the edge's weight, and a rating above it is refused. */
+		maxRating: z.number().positive()
+	}).strict(),
+	z.object({
+		format: z.literal("konect"),
+		encoding: z.literal("utf-8"),
+		/** Whether the third column is read as the edge's weight; the file's own weight type must agree. */
+		weighted: z.boolean(),
+		/** Whether the fourth column is read as the edge's time. */
+		timestamped: z.boolean()
+	}).strict(),
 	z.object({
 		format: z.literal("gml"),
 		encoding: EncodingSchema
@@ -613,6 +647,10 @@ const ParserSchema = z.discriminatedUnion("format", [
 		format: z.literal("vrp-rep"),
 		encoding: z.literal("utf-8")
 	}).strict(),
+	z.object({
+		format: z.literal("hhcrsp"),
+		encoding: z.literal("utf-8")
+	}).strict(),
 	z.object({
 		format: z.literal("csv-table"),
 		encoding: EncodingSchema,
@@ -1070,7 +1108,7 @@ 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": "1.24.0",
+		"version": "1.26.0",
 		"repository": "https://github.com/Mearman/keepset",
 		"namespaceAliases": {
 			"networkrepository": ["nr"],
@@ -1078,6 +1116,85 @@ var catalogue_default = {
 		}
 	},
 	crosswalks: {
+		"crosswalks/graph-v1/rated.json": {
+			"source": "keepset/rated",
+			"target": "graph/v1",
+			"rules": [
+				{
+					"op": "move",
+					"from": "meta",
+					"to": "meta"
+				},
+				{
+					"op": "move",
+					"from": "nodes[].id",
+					"to": "nodes[].id"
+				},
+				{
+					"op": "move",
+					"from": "edges[].source",
+					"to": "edges[].source"
+				},
+				{
+					"op": "move",
+					"from": "edges[].target",
+					"to": "edges[].target"
+				},
+				{
+					"op": "move",
+					"from": "nodes[].type",
+					"to": "nodes[].type"
+				},
+				{
+					"op": "move",
+					"from": "edges[].type",
+					"to": "edges[].type"
+				},
+				{
+					"op": "move",
+					"from": "edges[].weight",
+					"to": "edges[].weight"
+				},
+				{
+					"op": "move",
+					"from": "edges[].timestamp",
+					"to": "edges[].timestamp"
+				}
+			],
+			"oneWay": []
+		},
+		"crosswalks/graph-v1/timestamped.json": {
+			"source": "keepset/timestamped",
+			"target": "graph/v1",
+			"rules": [
+				{
+					"op": "move",
+					"from": "meta",
+					"to": "meta"
+				},
+				{
+					"op": "move",
+					"from": "nodes[].id",
+					"to": "nodes[].id"
+				},
+				{
+					"op": "move",
+					"from": "edges[].source",
+					"to": "edges[].source"
+				},
+				{
+					"op": "move",
+					"from": "edges[].target",
+					"to": "edges[].target"
+				},
+				{
+					"op": "move",
+					"from": "edges[].timestamp",
+					"to": "edges[].timestamp"
+				}
+			],
+			"oneWay": []
+		},
 		"crosswalks/graph-v1/topology.json": {
 			"source": "keepset/topology",
 			"target": "graph/v1",
@@ -1105,6 +1222,75 @@ var catalogue_default = {
 			],
 			"oneWay": []
 		},
+		"crosswalks/graph-v1/weighted-timestamped.json": {
+			"source": "keepset/weighted-timestamped",
+			"target": "graph/v1",
+			"rules": [
+				{
+					"op": "move",
+					"from": "meta",
+					"to": "meta"
+				},
+				{
+					"op": "move",
+					"from": "nodes[].id",
+					"to": "nodes[].id"
+				},
+				{
+					"op": "move",
+					"from": "edges[].source",
+					"to": "edges[].source"
+				},
+				{
+					"op": "move",
+					"from": "edges[].target",
+					"to": "edges[].target"
+				},
+				{
+					"op": "move",
+					"from": "edges[].weight",
+					"to": "edges[].weight"
+				},
+				{
+					"op": "move",
+					"from": "edges[].timestamp",
+					"to": "edges[].timestamp"
+				}
+			],
+			"oneWay": []
+		},
+		"crosswalks/graph-v1/weighted.json": {
+			"source": "keepset/weighted",
+			"target": "graph/v1",
+			"rules": [
+				{
+					"op": "move",
+					"from": "meta",
+					"to": "meta"
+				},
+				{
+					"op": "move",
+					"from": "nodes[].id",
+					"to": "nodes[].id"
+				},
+				{
+					"op": "move",
+					"from": "edges[].source",
+					"to": "edges[].source"
+				},
+				{
+					"op": "move",
+					"from": "edges[].target",
+					"to": "edges[].target"
+				},
+				{
+					"op": "move",
+					"from": "edges[].weight",
+					"to": "edges[].weight"
+				}
+			],
+			"oneWay": []
+		},
 		"crosswalks/tasks-v1/nodes.json": {
 			"source": "keepset/nodes",
 			"target": "tasks/v1",
@@ -1560,10 +1746,19 @@ var catalogue_default = {
 			"licence": { "kind": "unrecorded" },
 			"citations": [{ "text": "McAuley, Julian, Targett, Christopher, Shi, Qinfeng, van den Hengel, Anton (2015). Image-Based Recommendations on Styles and Substitutes. Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (amazon-ratings: format amazon-ratings has a pipeline-specific parser with no declarative keepset form yet)"
+				"status": "fetchable",
+				"source": 0,
+				"archive": { "kind": "none" },
+				"parser": {
+					"format": "user-item-ratings",
+					"encoding": "utf-8",
+					"delimiter": "comma",
+					"skipLines": 0,
+					"itemType": "product",
+					"maxRating": 5
+				}
 			},
-			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
+			"crosswalk": { "file": "crosswalks/graph-v1/rated.json" },
 			"expectedCounts": {
 				"edges": 2023070,
 				"nodes": 1459545
@@ -1597,10 +1792,19 @@ var catalogue_default = {
 			"licence": { "kind": "unrecorded" },
 			"citations": [{ "text": "McAuley, Julian, Targett, Christopher, Shi, Qinfeng, van den Hengel, Anton (2015). Image-Based Recommendations on Styles and Substitutes. Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (amazon-ratings: format amazon-ratings has a pipeline-specific parser with no declarative keepset form yet)"
+				"status": "fetchable",
+				"source": 0,
+				"archive": { "kind": "none" },
+				"parser": {
+					"format": "user-item-ratings",
+					"encoding": "utf-8",
+					"delimiter": "comma",
+					"skipLines": 0,
+					"itemType": "product",
+					"maxRating": 5
+				}
 			},
-			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
+			"crosswalk": { "file": "crosswalks/graph-v1/rated.json" },
 			"expectedCounts": {
 				"edges": 836006,
 				"nodes": 744649
@@ -1660,7 +1864,7 @@ var catalogue_default = {
 		{
 			"id": "amazon-movies-tv",
 			"name": "Amazon Movies and TV Reviews",
-			"description": "Directed bipartite user-product review network for Movies and TV on Amazon. Users are linked to products they reviewed; edge weights are normalised star ratings.",
+			"description": "Undirected bipartite user-product review network for Movies and TV on Amazon. Users are linked to products they reviewed; edge weights are normalised star ratings.",
 			"tags": [],
 			"category": "graph/v1",
 			"sources": [{
@@ -1671,10 +1875,19 @@ var catalogue_default = {
 			"licence": { "kind": "unrecorded" },
 			"citations": [{ "text": "McAuley, Julian, Targett, Christopher, Shi, Qinfeng, van den Hengel, Anton (2015). Image-Based Recommendations on Styles and Substitutes. Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (amazon-ratings-undirected: format amazon-ratings-undirected has a pipeline-specific parser with no declarative keepset form yet)"
+				"status": "fetchable",
+				"source": 0,
+				"archive": { "kind": "none" },
+				"parser": {
+					"format": "user-item-ratings",
+					"encoding": "utf-8",
+					"delimiter": "comma",
+					"skipLines": 0,
+					"itemType": "product",
+					"maxRating": 5
+				}
 			},
-			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
+			"crosswalk": { "file": "crosswalks/graph-v1/rated.json" },
 			"expectedCounts": {
 				"edges": 4607047,
 				"nodes": 2289561
@@ -1708,10 +1921,19 @@ var catalogue_default = {
 			"licence": { "kind": "unrecorded" },
 			"citations": [{ "text": "McAuley, Julian, Targett, Christopher, Shi, Qinfeng, van den Hengel, Anton (2015). Image-Based Recommendations on Styles and Substitutes. Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (amazon-ratings: format amazon-ratings has a pipeline-specific parser with no declarative keepset form yet)"
+				"status": "fetchable",
+				"source": 0,
+				"archive": { "kind": "none" },
+				"parser": {
+					"format": "user-item-ratings",
+					"encoding": "utf-8",
+					"delimiter": "comma",
+					"skipLines": 0,
+					"itemType": "product",
+					"maxRating": 5
+				}
 			},
-			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
+			"crosswalk": { "file": "crosswalks/graph-v1/rated.json" },
 			"expectedCounts": {
 				"edges": 500176,
 				"nodes": 422277
@@ -1745,10 +1967,19 @@ var catalogue_default = {
 			"licence": { "kind": "unrecorded" },
 			"citations": [{ "text": "McAuley, Julian, Targett, Christopher, Shi, Qinfeng, van den Hengel, Anton (2015). Image-Based Recommendations on Styles and Substitutes. Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (amazon-ratings: format amazon-ratings has a pipeline-specific parser with no declarative keepset form yet)"
+				"status": "fetchable",
+				"source": 0,
+				"archive": { "kind": "none" },
+				"parser": {
+					"format": "user-item-ratings",
+					"encoding": "utf-8",
+					"delimiter": "comma",
+					"skipLines": 0,
+					"itemType": "product",
+					"maxRating": 5
+				}
 			},
-			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
+			"crosswalk": { "file": "crosswalks/graph-v1/rated.json" },
 			"expectedCounts": {
 				"edges": 1324753,
 				"nodes": 876977
@@ -7036,10 +7267,111 @@ var catalogue_default = {
 			},
 			"citations": [],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "The download is a per-request zip of a point shapefile (the attributes are in a dbf and the positions in a separate shp, in a projected system) with no CSV or GeoJSON route, and keepset has no shapefile parser."
+				"status": "fetchable",
+				"source": 1,
+				"archive": {
+					"kind": "shapefile",
+					"member": { "path": "dataset/L_SITADEL_LOGEMENT_R11.shp" }
+				},
+				"parser": {
+					"format": "csv-table",
+					"encoding": "utf-8",
+					"delimiter": "comma",
+					"skipLines": 0,
+					"idColumn": "id",
+					"numericColumns": [
+						{
+							"column": "geometry_latitude",
+							"factor": 1
+						},
+						{
+							"column": "geometry_longitude",
+							"factor": 1
+						},
+						{
+							"column": "geometry_x",
+							"factor": 1
+						},
+						{
+							"column": "geometry_y",
+							"factor": 1
+						}
+					],
+					"columns": [
+						"date_ree_2",
+						"geometry_latitude",
+						"geometry_longitude",
+						"date_reell",
+						"type_dau",
+						"etat_dau",
+						"comm",
+						"geometry_x",
+						"geometry_y"
+					]
+				}
+			},
+			"crosswalk": {
+				"source": "csv-table",
+				"target": "tasks/v1",
+				"rules": [
+					{
+						"op": "move",
+						"from": "meta",
+						"to": "meta"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].id",
+						"to": "nodes[].id"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].date_ree_2",
+						"to": "nodes[].closed"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].geometry_latitude",
+						"to": "nodes[].lat"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].geometry_longitude",
+						"to": "nodes[].lon"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].date_reell",
+						"to": "nodes[].opened"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].type_dau",
+						"to": "nodes[].skill"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].etat_dau",
+						"to": "nodes[].status"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].comm",
+						"to": "nodes[].territory"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].geometry_x",
+						"to": "nodes[].x"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].geometry_y",
+						"to": "nodes[].y"
+					}
+				],
+				"oneWay": []
 			},
-			"crosswalk": { "file": "crosswalks/tasks-v1/nodes.json" },
 			"expectedCounts": {},
 			"properties": { "surveyId": "or-72" }
 		},
@@ -8824,7 +9156,7 @@ var catalogue_default = {
 			"namespace": ["konect"],
 			"aliases": ["opsahl-collaboration"],
 			"name": "Opsahl Collaboration Network",
-			"description": "Undirected weighted co-authorship network from the arXiv. Edge weights represent the number of papers co-authored by each pair of researchers, making it genuinely weighted.",
+			"description": "Bipartite authorship network of the arXiv condensed matter section (cond-mat) from 1995 to 1999: an edge joins an author, a left node, and a paper they wrote, a right node. The network is unweighted and has no repeated pairs.",
 			"tags": [],
 			"category": "graph/v1",
 			"sources": [{
@@ -8835,27 +9167,37 @@ var catalogue_default = {
 			"licence": { "kind": "unrecorded" },
 			"citations": [{ "text": "Opsahl, Tore (2013). Triadic closure in two-mode networks: Redefining the global and local clustering coefficients. Social Networks." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (konect-tarbz2: bzip2 compression has no keepset unpacker yet)"
+				"status": "fetchable",
+				"source": 0,
+				"archive": {
+					"kind": "tar.bz2",
+					"member": { "pattern": "(?:[^/]+/)?out\\.[^/]+" }
+				},
+				"parser": {
+					"format": "konect",
+					"encoding": "utf-8",
+					"weighted": false,
+					"timestamped": false
+				}
 			},
 			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
 			"expectedCounts": {
 				"edges": 58595,
-				"nodes": 22015
+				"nodes": 38741
 			},
 			"properties": {
-				"components": 1,
-				"connected": true,
+				"components": 1188,
+				"connected": false,
 				"cyclic": true,
-				"density": .00024177210459736553,
+				"density": 7808365090394136e-20,
 				"directed": false,
 				"edgeTypes": 1,
 				"heterogeneous": false,
-				"multigraph": true,
+				"multigraph": false,
 				"nodeTypes": 1,
 				"rawBytes": 0,
-				"selfLoops": true,
-				"weighted": true
+				"selfLoops": false,
+				"weighted": false
 			}
 		},
 		{
@@ -8875,10 +9217,20 @@ var catalogue_default = {
 			"licence": { "kind": "unrecorded" },
 			"citations": [{ "text": "Panzarasa, Pietro, Opsahl, Tore, Carley, Kathleen M. (2009). Patterns and dynamics of users' behavior and interaction: Network analysis of an online community. Journal of the American Society for Information Science and Technology 60(5), 911-932." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (konect-tarbz2: bzip2 compression has no keepset unpacker yet)"
+				"status": "fetchable",
+				"source": 0,
+				"archive": {
+					"kind": "tar.bz2",
+					"member": { "pattern": "(?:[^/]+/)?out\\.[^/]+" }
+				},
+				"parser": {
+					"format": "konect",
+					"encoding": "utf-8",
+					"weighted": false,
+					"timestamped": true
+				}
 			},
-			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
+			"crosswalk": { "file": "crosswalks/graph-v1/timestamped.json" },
 			"expectedCounts": {
 				"edges": 59835,
 				"nodes": 1899
@@ -8909,10 +9261,20 @@ var catalogue_default = {
 			"licence": { "kind": "unrecorded" },
 			"citations": [{ "text": "M. Michalski (2010). Manufacturing Company Emails." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (tsv: bzip2 compression has no keepset unpacker yet)"
+				"status": "fetchable",
+				"source": 0,
+				"archive": {
+					"kind": "tar.bz2",
+					"member": { "pattern": "(?:[^/]+/)?out\\.[^/]+" }
+				},
+				"parser": {
+					"format": "konect",
+					"encoding": "utf-8",
+					"weighted": false,
+					"timestamped": true
+				}
 			},
-			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
+			"crosswalk": { "file": "crosswalks/graph-v1/timestamped.json" },
 			"expectedCounts": {
 				"edges": 82927,
 				"nodes": 167
@@ -8942,8 +9304,18 @@ var catalogue_default = {
 			"licence": { "kind": "unrecorded" },
 			"citations": [{ "text": "R. West, J. Leskovec (2012). Human Wayfinding in Information Networks. Proceedings of the 21st International Conference on World Wide Web, 619-628." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (tsv: bzip2 compression has no keepset unpacker yet)"
+				"status": "fetchable",
+				"source": 0,
+				"archive": {
+					"kind": "tar.bz2",
+					"member": { "pattern": "(?:[^/]+/)?out\\.[^/]+" }
+				},
+				"parser": {
+					"format": "konect",
+					"encoding": "utf-8",
+					"weighted": false,
+					"timestamped": false
+				}
 			},
 			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
 			"expectedCounts": {
@@ -9414,10 +9786,20 @@ var catalogue_default = {
 			"licence": { "kind": "unrecorded" },
 			"citations": [{ "text": "Donald E. Knuth (1993). The Stanford GraphBase: A Platform for Combinatorial Computing. Addison-Wesley." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (konect-tarbz2: bzip2 compression has no keepset unpacker yet)"
+				"status": "fetchable",
+				"source": 0,
+				"archive": {
+					"kind": "tar.bz2",
+					"member": { "pattern": "(?:[^/]+/)?out\\.[^/]+" }
+				},
+				"parser": {
+					"format": "konect",
+					"encoding": "utf-8",
+					"weighted": true,
+					"timestamped": false
+				}
 			},
-			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
+			"crosswalk": { "file": "crosswalks/graph-v1/weighted.json" },
 			"expectedCounts": {
 				"edges": 254,
 				"nodes": 77
@@ -10410,7 +10792,7 @@ var catalogue_default = {
 			}],
 			"recipe": {
 				"status": "not-fetchable",
-				"reason": "The downloads are MATLAB data files and keepset has no parser for them."
+				"reason": "Each instance is a MATLAB 5 file whose orders, the nodes with their quantities, mix codes and delivery times, are a MATLAB table of datetime and other class objects, which MATLAB stores in the file's undocumented MCOS subsystem data rather than as arrays; the only plain arrays are the travel time and distance matrices, so nothing at node level can be read without reverse engineering that serialisation."
 			},
 			"crosswalk": { "file": "crosswalks/tasks-v1/nodes.json" },
 			"expectedCounts": {},
@@ -10595,6 +10977,10 @@ var catalogue_default = {
 				"url": "https://data.mendeley.com/datasets/hp3xftsrfx/1",
 				"retrieved": "2026-10-19",
 				"status": "live"
+			}, {
+				"url": "https://data.mendeley.com/public-api/zip/hp3xftsrfx/download/2",
+				"retrieved": "2026-10-19",
+				"status": "live"
 			}],
 			"licence": {
 				"kind": "spdx",
@@ -10608,12 +10994,93 @@ var catalogue_default = {
 				"doi": "10.1007/s10729-013-9243-1"
 			}],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "The download is a RAR archive of macro enabled Excel workbooks, and keepset reads neither RAR archives nor macro workbooks."
+				"status": "fetchable",
+				"source": 1,
+				"archive": {
+					"kind": "zip",
+					"members": { "extensions": [".xlsm"] },
+					"inner": {
+						"kind": "xlsx",
+						"sheets": "(?!G5$|J5$).+"
+					}
+				},
+				"parser": {
+					"format": "hhcrsp",
+					"encoding": "utf-8"
+				}
 			},
-			"crosswalk": { "file": "crosswalks/tasks-v1/nodes.json" },
-			"expectedCounts": {},
-			"properties": { "surveyId": "or-16" }
+			"crosswalk": {
+				"source": "hhcrsp",
+				"target": "tasks/v1",
+				"rules": [
+					{
+						"op": "move",
+						"from": "meta",
+						"to": "meta"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].id",
+						"to": "nodes[].id"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].services",
+						"to": "nodes[].skill"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].x",
+						"to": "nodes[].x"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].y",
+						"to": "nodes[].y"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].role",
+						"to": "nodes[].role"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].duration1",
+						"to": "nodes[].duration1"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].duration2",
+						"to": "nodes[].duration2"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].earliest1",
+						"to": "nodes[].earliest1"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].latest1",
+						"to": "nodes[].latest1"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].earliest2",
+						"to": "nodes[].earliest2"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].latest2",
+						"to": "nodes[].latest2"
+					}
+				],
+				"oneWay": []
+			},
+			"expectedCounts": { "instances": 82 },
+			"properties": {
+				"surveyId": "or-16",
+				"timeUnit": "abstract units"
+			}
 		},
 		{
 			"id": "mendeley-data-last-mile-delivery-route-deviations",
@@ -11479,10 +11946,22 @@ var catalogue_default = {
 			},
 			"citations": [{ "text": "F. Maxwell Harper, Joseph A. Konstan (2016). The MovieLens Datasets: History and Context. ACM Transactions on Interactive Intelligent Systems." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (movielens: format movielens has a pipeline-specific parser with no declarative keepset form yet)"
+				"status": "fetchable",
+				"source": 0,
+				"archive": {
+					"kind": "zip",
+					"member": { "path": "u.data" }
+				},
+				"parser": {
+					"format": "user-item-ratings",
+					"encoding": "utf-8",
+					"delimiter": "tab",
+					"skipLines": 0,
+					"itemType": "movie",
+					"maxRating": 5
+				}
 			},
-			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
+			"crosswalk": { "file": "crosswalks/graph-v1/rated.json" },
 			"expectedCounts": {
 				"edges": 1e5,
 				"nodes": 2625
@@ -11505,7 +11984,7 @@ var catalogue_default = {
 		{
 			"id": "movielens-10m",
 			"name": "MovieLens 10M User-Movie Ratings",
-			"description": "Bipartite user-movie rating network from the GroupLens research group. 10,000,054 ratings from 71,567 users on 10,681 movies. Edge weights are ratings normalised to [0, 1].",
+			"description": "Bipartite user-movie rating network from the GroupLens research group. 10,000,054 ratings from 69,878 users on 10,677 movies. Edge weights are ratings normalised to [0, 1].",
 			"tags": [],
 			"category": "graph/v1",
 			"sources": [{
@@ -11520,10 +11999,22 @@ var catalogue_default = {
 			},
 			"citations": [{ "text": "Harper, F. Maxwell, Konstan, Joseph A. (2016). The MovieLens Datasets: History and Context. ACM Transactions on Interactive Intelligent Systems." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (movielens: format movielens has a pipeline-specific parser with no declarative keepset form yet)"
+				"status": "fetchable",
+				"source": 0,
+				"archive": {
+					"kind": "zip",
+					"member": { "path": "ratings.dat" }
+				},
+				"parser": {
+					"format": "user-item-ratings",
+					"encoding": "utf-8",
+					"delimiter": "double-colon",
+					"skipLines": 0,
+					"itemType": "movie",
+					"maxRating": 5
+				}
 			},
-			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
+			"crosswalk": { "file": "crosswalks/graph-v1/rated.json" },
 			"expectedCounts": {
 				"edges": 10000054,
 				"nodes": 80555
@@ -11546,7 +12037,7 @@ var catalogue_default = {
 		{
 			"id": "movielens-1m",
 			"name": "MovieLens 1M User-Movie Ratings",
-			"description": "Bipartite user-movie rating network from the GroupLens research group. 1,000,209 ratings from 6,040 users on 3,900 movies. Edge weights are ratings normalised to [0, 1].",
+			"description": "Bipartite user-movie rating network from the GroupLens research group. 1,000,209 ratings from 6,040 users on 3,706 movies. Edge weights are ratings normalised to [0, 1].",
 			"tags": [],
 			"category": "graph/v1",
 			"sources": [{
@@ -11561,10 +12052,22 @@ var catalogue_default = {
 			},
 			"citations": [{ "text": "Harper, F. Maxwell, Konstan, Joseph A. (2016). The MovieLens Datasets: History and Context. ACM Transactions on Interactive Intelligent Systems." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (movielens: format movielens has a pipeline-specific parser with no declarative keepset form yet)"
+				"status": "fetchable",
+				"source": 0,
+				"archive": {
+					"kind": "zip",
+					"member": { "path": "ratings.dat" }
+				},
+				"parser": {
+					"format": "user-item-ratings",
+					"encoding": "utf-8",
+					"delimiter": "double-colon",
+					"skipLines": 0,
+					"itemType": "movie",
+					"maxRating": 5
+				}
 			},
-			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
+			"crosswalk": { "file": "crosswalks/graph-v1/rated.json" },
 			"expectedCounts": {
 				"edges": 1000209,
 				"nodes": 9746
@@ -11587,7 +12090,7 @@ var catalogue_default = {
 		{
 			"id": "movielens-25m",
 			"name": "MovieLens 25M User-Movie Ratings",
-			"description": "Bipartite user-movie rating network from the GroupLens research group. 25,000,095 ratings from 162,541 users on 62,423 movies. Edge weights are ratings normalised to [0, 1].",
+			"description": "Bipartite user-movie rating network from the GroupLens research group. 25,000,095 ratings from 162,541 users on 59,047 movies. Edge weights are ratings normalised to [0, 1].",
 			"tags": [],
 			"category": "graph/v1",
 			"sources": [{
@@ -11603,7 +12106,7 @@ var catalogue_default = {
 			"citations": [{ "text": "Harper, F. Maxwell, Konstan, Joseph A. (2016). The MovieLens Datasets: History and Context. ACM Transactions on Interactive Intelligent Systems." }],
 			"recipe": {
 				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (movielens: format movielens has a pipeline-specific parser with no declarative keepset form yet)"
+				"reason": "no download is in a form keepset reads yet (movielens: the ratings file has more edges than one fetch can hold: the crosswalk step aborts on it with an allocation failure (ExaDev/crossmap#57), where ml-10m completes)"
 			},
 			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
 			"expectedCounts": {
@@ -17707,7 +18210,7 @@ var catalogue_default = {
 			"citations": [],
 			"recipe": {
 				"status": "not-fetchable",
-				"reason": "The source is an SRU search endpoint that returns XML notices in a query language and not a table, and keepset has no parser for it."
+				"reason": "The source is an SRU search interface whose Gemeenteblad environmental permit notices are a result set of well over a million records, while the interface serves at most 100 records a request and none past the 10,000th of a result set; a fetch would have to split the query by date into hundreds of windows and make more than ten thousand requests for gigabytes of XML, which no recipe reads, and a single window of the set is not this dataset."
 			},
 			"crosswalk": { "file": "crosswalks/tasks-v1/nodes.json" },
 			"expectedCounts": {},