keepset 0.37.1 → 0.39.0

package/dist/{bundled-CRr7GPD3.js → bundled-6dYCPVD-.js}

@@ -523,11 +523,30 @@ const CollectionArchiveSchema = z.object({
 		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({
+/** An archive whose dataset is spread over several of its files, which a parser of a multi-file format (`ogb`) reads together into one document: every file the `files` selector matches, at least one, in path order, each gunzipped first when `inner` says so (an OGB dataset zip holds its tables as `.csv.gz` files). */
+const FilesArchiveSchema = z.object({
 	kind: FileArchiveKindSchema,
-	member: ArchiveMemberSchema
-}).strict()]);
+	files: ArchiveMemberSchema,
+	inner: z.object({ kind: z.literal("gzip") }).strict().optional()
+}).strict();
+/** A spreadsheet read as the CSV of one of its sheets (the sheet's name, as the workbook gives it): an Excel workbook (`xlsx`), a legacy binary Excel 97 to 2003 workbook (`xls`, BIFF8) or an OpenDocument spreadsheet (`ods`, whose sheets are its tables). The three give the same text for the same cells. */
+const SheetArchiveSchema = z.object({
+	kind: z.enum([
+		"xlsx",
+		"xls",
+		"ods"
+	]),
+	sheet: z.string().min(1)
+}).strict();
+/** How a member that is itself an archive unpacks into the file the parser reads: gunzipped, one member of it selected, or one sheet of it read when it is a spreadsheet. 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(),
+	SheetArchiveSchema
+]);
 /** The name of a part of a document read from several files, which the parser gives its meaning: the split a triples file holds (`train`, `valid`, `test`), or which of an HGB dataset's files it is (`nodes`, `links`). */
 const PartNameSchema = z.string().regex(/^[a-z][a-z0-9]*$/, { message: "must be a lowercase name of letters and digits, such as train" });
 /** An archive one document is read from several files of: each part names the one member it is read from, and the parser reads the parts together in the order given. */
@@ -538,7 +557,7 @@ const PartsArchiveSchema = z.object({
 		member: ArchiveMemberSchema
 	}).strict()).min(1).refine((parts) => new Set(parts.map((part) => part.name)).size === parts.length, { message: "each part must have its own name" })
 }).strict();
-/** How the downloaded bytes unpack into the file the parser reads, the named files a parser reads together into one document (`parts`), 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. */
+/** How the downloaded bytes unpack into the file the parser reads, the named files a parser of a parts format reads together into one document (`parts`, such as the split files of a triples download or an HGB dataset's nodes and links), the files a parser of a multi-file format reads together into one document (`files`, such as an OGB raw directory), 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, a spreadsheet inside a zip) is unpacked by `inner`. A spreadsheet (`xlsx`, `xls` or `ods`) is read as the CSV of its named sheet, with dates as ISO 8601 text, for the `csv-table` or `edge-list` 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(),
@@ -550,10 +569,8 @@ const ArchiveSchema = z.union([
 	}).strict(),
 	CollectionArchiveSchema,
 	PartsArchiveSchema,
-	z.object({
-		kind: z.literal("xlsx"),
-		sheet: z.string().min(1)
-	}).strict(),
+	FilesArchiveSchema,
+	SheetArchiveSchema,
 	z.object({
 		kind: z.literal("shapefile"),
 		member: ArchiveMemberSchema
@@ -579,10 +596,31 @@ const ParserSchema = z.discriminatedUnion("format", [
 		skipLines: z.int().min(0),
 		commentPrefixes: z.array(z.string().min(1)),
 		sourceColumn: ColumnSchema,
-		targetColumn: ColumnSchema
+		targetColumn: ColumnSchema,
+		/** Keep only the lines whose `column` holds one of `values`, so a table that lists several relations side by side (a connectome's synapse types) gives the graph of the ones named. */
+		keep: z.object({
+			column: ColumnSchema,
+			values: z.array(z.string().min(1)).min(1)
+		}).strict().optional(),
+		/** The column holding how many edges a line stands for, a whole number, for a table that lists each pair once with its count; a line that stands for none adds neither an edge nor a node. */
+		multiplicityColumn: ColumnSchema.optional(),
+		/** The table lists every undirected edge twice, once in each direction and with the same multiplicity: each pair's edges are emitted once, in the direction it is first listed, a self-loop's once, and a line whose mirror is missing is an error. graph/v1 records direction in `meta` and never by duplicating edges, so an undirected graph read from such a table needs this. */
+		mirrored: z.literal(true).optional(),
+		/** The conditions a data line must meet to be an edge, each a column whose trimmed field equals a value; a file whose rows are of several kinds (an interaction file listing genetic beside physical interactions, or interactions with another organism's proteins) is read for the rows the dataset is made of. Without it every data line is an edge. */
+		where: z.array(z.object({
+			column: ColumnSchema,
+			equals: z.string().min(1)
+		}).strict()).min(1).optional()
 	}).strict().refine((parser) => parser.sourceColumn !== parser.targetColumn, {
 		message: "sourceColumn and targetColumn must differ",
 		path: ["targetColumn"]
+	}).refine((parser) => [
+		parser.keep?.column,
+		parser.multiplicityColumn,
+		...(parser.where ?? []).map((condition) => condition.column)
+	].every((column) => column === void 0 || column !== parser.sourceColumn && column !== parser.targetColumn), {
+		message: "the keep, multiplicity and where columns must not be an endpoint column",
+		path: ["keep"]
 	}),
 	z.object({
 		format: z.literal("matrix-market"),
@@ -674,6 +712,14 @@ const ParserSchema = z.discriminatedUnion("format", [
 		format: z.literal("gd-contest"),
 		encoding: EncodingSchema
 	}).strict(),
+	z.object({
+		format: z.literal("witvliet-synapses"),
+		encoding: z.literal("utf-8")
+	}).strict(),
+	z.object({
+		format: z.literal("ogb"),
+		encoding: z.literal("utf-8")
+	}).strict(),
 	z.object({
 		format: z.literal("customer-points"),
 		encoding: EncodingSchema
@@ -773,6 +819,8 @@ const PagingSchema = z.discriminatedUnion("kind", [
 		pageSize: z.int().min(1)
 	}).strict()
 ]);
+/** The parser formats that read a dataset spread over several files of one archive, and so the only ones a `files` archive is given to. */
+const MULTI_FILE_FORMATS = /* @__PURE__ */ new Set(["ogb"]);
 /** 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. */
 /** The parser formats that read a document from named parts, and the part names each requires (none for a format whose part names are its own, such as the splits of a triples download). */
 const PART_FORMATS = /* @__PURE__ */ new Map([["kg-triples", void 0], ["hgb", ["nodes", "links"]]]);
@@ -797,6 +845,11 @@ const RecipeSchema = z.discriminatedUnion("status", [z.object({
 			message: `the ${recipe.parser.format} parser reads the parts ${required.join(" and ")} from a parts archive`
 		});
 	}
+	if ("files" in recipe.archive !== MULTI_FILE_FORMATS.has(recipe.parser.format)) ctx.addIssue({
+		code: "custom",
+		path: ["archive"],
+		message: `a files archive is read by a multi-file parser (${[...MULTI_FILE_FORMATS].join(", ")}), and such a parser reads only a files archive`
+	});
 }), z.object({
 	status: z.literal("not-fetchable"),
 	reason: z.string().min(1)
@@ -1180,7 +1233,7 @@ 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": "1.28.0",
+		"version": "1.30.0",
 		"repository": "https://github.com/Mearman/keepset",
 		"namespaceAliases": {
 			"networkrepository": ["nr"],
@@ -2437,7 +2490,7 @@ var catalogue_default = {
 			"citations": [{ "text": "Jie Tang, Jing Zhang, Limin Yao, Juanzi Li, Li Zhang, Zhong Su (2008). ArnetMiner: Extraction and Mining of Academic Social Networks. Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining." }],
 			"recipe": {
 				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (aminer-7z: 7z compression has no keepset unpacker yet)"
+				"reason": "no download is in a form keepset reads yet (aminer-7z: the archive is a 7z (LZMA2) file holding one JSON array of paper records (dblp.v12.json) that unpacks to over twelve gigabytes, more than a fetch can hold in memory, so no 7z reader is added for it)"
 			},
 			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
 			"expectedCounts": {
@@ -2530,8 +2583,21 @@ var catalogue_default = {
 			"licence": { "kind": "unrecorded" },
 			"citations": [{ "text": "R. Guimera, L. Danon, A. Diaz-Guilera, F. Giralt, A. Arenas (2003). Self-similar community structure in a network of human interactions. Physical Review E 68, 065103(R)." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (various: an archive in format various, whose member and format the catalogue does not record)"
+				"status": "fetchable",
+				"source": 0,
+				"archive": {
+					"kind": "zip",
+					"member": { "path": "email.txt" }
+				},
+				"parser": {
+					"format": "edge-list",
+					"encoding": "utf-8",
+					"delimiter": "whitespace",
+					"skipLines": 0,
+					"commentPrefixes": ["#", "%"],
+					"sourceColumn": 0,
+					"targetColumn": 1
+				}
 			},
 			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
 			"expectedCounts": {
@@ -6451,6 +6517,10 @@ var catalogue_default = {
 				"url": "https://environment.data.gov.uk/dataset/88bed270-d465-11e4-8669-f0def148f590",
 				"retrieved": "2026-10-19",
 				"status": "live"
+			}, {
+				"url": "https://environment.data.gov.uk/api/file/download?fileDataSetId=766cb094-b392-4bd6-a02e-f60e143f3213&fileName=Historic_Flood_Warnings.zip",
+				"retrieved": "2026-10-19",
+				"status": "live"
 			}],
 			"licence": {
 				"kind": "spdx",
@@ -6458,10 +6528,62 @@ var catalogue_default = {
 			},
 			"citations": [],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "The download is a zip holding one OpenDocument spreadsheet whose member name changes every quarter, and keepset reads xlsx and not ods."
+				"status": "fetchable",
+				"source": 1,
+				"archive": {
+					"kind": "zip",
+					"member": { "extensions": [".ods"] },
+					"inner": {
+						"kind": "ods",
+						"sheet": "tblAllData"
+					}
+				},
+				"parser": {
+					"format": "csv-table",
+					"encoding": "utf-8",
+					"delimiter": "comma",
+					"skipLines": 0,
+					"idColumn": null,
+					"numericColumns": [],
+					"columns": [
+						"DATE",
+						"TYPE",
+						"AREA"
+					]
+				}
+			},
+			"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",
+						"to": "nodes[].opened"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].TYPE",
+						"to": "nodes[].status"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].AREA",
+						"to": "nodes[].territory"
+					}
+				],
+				"oneWay": []
 			},
-			"crosswalk": { "file": "crosswalks/tasks-v1/nodes.json" },
 			"expectedCounts": {},
 			"properties": { "surveyId": "or-120" }
 		},
@@ -8470,6 +8592,10 @@ var catalogue_default = {
 				"url": "https://github.com/Oberfichtner/Clustering_and_TSP_with_R",
 				"retrieved": "2026-10-19",
 				"status": "live"
+			}, {
+				"url": "https://raw.githubusercontent.com/Oberfichtner/Clustering_and_TSP_with_R/main/rawdataclear.xls",
+				"retrieved": "2026-10-19",
+				"status": "live"
 			}],
 			"licence": { "kind": "unrecorded" },
 			"citations": [{
@@ -8477,11 +8603,56 @@ var catalogue_default = {
 				"doi": "10.1007/s10479-022-04883-1"
 			}],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "The only data file is an old binary xls workbook, and keepset reads only xlsx."
+				"status": "fetchable",
+				"source": 1,
+				"archive": {
+					"kind": "xls",
+					"sheet": "objects"
+				},
+				"parser": {
+					"format": "csv-table",
+					"encoding": "utf-8",
+					"delimiter": "comma",
+					"skipLines": 0,
+					"idColumn": null,
+					"numericColumns": [{
+						"column": "LATITUDE",
+						"factor": 1
+					}, {
+						"column": "LONGITUDE",
+						"factor": 1
+					}],
+					"columns": ["LATITUDE", "LONGITUDE"]
+				}
 			},
-			"crosswalk": { "file": "crosswalks/tasks-v1/nodes.json" },
-			"expectedCounts": {},
+			"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[].LATITUDE",
+						"to": "nodes[].lat"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].LONGITUDE",
+						"to": "nodes[].lon"
+					}
+				],
+				"oneWay": []
+			},
+			"expectedCounts": { "nodes": 237 },
 			"properties": { "surveyId": "or-38" }
 		},
 		{
@@ -9276,7 +9447,7 @@ var catalogue_default = {
 			"citations": [{ "text": "Junheng Lin, Yibin Shen, Yifan Wang, Fangzhao Wu, Xiang Wang (2024). H2GB: A Hierarchical Heterogeneous Graph Benchmark for Node Property Prediction. Proceedings of the AAAI Conference on Artificial Intelligence." }],
 			"recipe": {
 				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (ieee-cis-zip: format ieee-cis-zip has a pipeline-specific parser with no declarative keepset form yet)"
+				"reason": "no download is in a form keepset reads yet (ieee-cis-zip: the archive holds the IEEE-CIS fraud detection competition's raw transaction and identity tables, not a graph: H2GB builds its graph from shared card, address, email and device fields with its own construction code)"
 			},
 			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
 			"expectedCounts": {
@@ -18485,7 +18656,7 @@ var catalogue_default = {
 			"citations": [{ "text": "Junheng Lin, Yibin Shen, Yifan Wang, Fangzhao Wu, Xiang Wang (2024). H2GB: A Hierarchical Heterogeneous Graph Benchmark for Node Property Prediction. Proceedings of the AAAI Conference on Artificial Intelligence." }],
 			"recipe": {
 				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (pytorch-hetero: format pytorch-hetero has a pipeline-specific parser with no declarative keepset form yet)"
+				"reason": "no download is in a form keepset reads yet (pytorch-hetero: the file is a PyTorch torch.save archive whose graph is a pickled Python dictionary (pyHGT's OAG layout of node_forward, node_feature and edge_list by target type, source type and relation), which only a Python runtime with PyTorch can unpickle, and it is several gigabytes)"
 			},
 			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
 			"expectedCounts": {
@@ -18517,6 +18688,10 @@ var catalogue_default = {
 				"url": "https://data.pyg.org/datasets/ogbl_biokg.zip",
 				"retrieved": "2026-03-26",
 				"status": "live"
+			}, {
+				"url": "https://snap.stanford.edu/ogb/data/linkproppred/biokg.zip",
+				"retrieved": "2026-10-21",
+				"status": "live"
 			}],
 			"licence": {
 				"kind": "spdx",
@@ -18524,8 +18699,17 @@ var catalogue_default = {
 			},
 			"citations": [{ "text": "Hu et al. (2020). Open Graph Benchmark: Datasets for Machine Learning on Graphs. NeurIPS." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (ogb-zip: format ogb-zip has a pipeline-specific parser with no declarative keepset form yet)"
+				"status": "fetchable",
+				"source": 1,
+				"archive": {
+					"kind": "zip",
+					"files": { "pattern": "[^/]+/raw/(?:num-node-list|num-node-dict|edge|num-edge-list|triplet-type-list|relations/[^/]+/(?:edge|num-edge-list))\\.csv\\.gz" },
+					"inner": { "kind": "gzip" }
+				},
+				"parser": {
+					"format": "ogb",
+					"encoding": "utf-8"
+				}
 			},
 			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
 			"expectedCounts": {
@@ -18565,8 +18749,17 @@ var catalogue_default = {
 			},
 			"citations": [{ "text": "Weihua Hu, Matthias Fey, Marinka Zitnik, Yuxiao Dong, Hongyu Ren, Bowen Liu, Michele Catasta, Jure Leskovec (2020). Open Graph Benchmark: Datasets for Machine Learning on Graphs. NeurIPS." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (ogb: format ogb has a pipeline-specific parser with no declarative keepset form yet)"
+				"status": "fetchable",
+				"source": 0,
+				"archive": {
+					"kind": "zip",
+					"files": { "pattern": "[^/]+/raw/(?:num-node-list|num-node-dict|edge|num-edge-list|triplet-type-list|relations/[^/]+/(?:edge|num-edge-list))\\.csv\\.gz" },
+					"inner": { "kind": "gzip" }
+				},
+				"parser": {
+					"format": "ogb",
+					"encoding": "utf-8"
+				}
 			},
 			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
 			"expectedCounts": {
@@ -18638,6 +18831,10 @@ var catalogue_default = {
 				"url": "https://data.pyg.org/datasets/ogbn_mag.zip",
 				"retrieved": "2026-03-26",
 				"status": "live"
+			}, {
+				"url": "https://snap.stanford.edu/ogb/data/nodeproppred/mag.zip",
+				"retrieved": "2026-10-21",
+				"status": "live"
 			}],
 			"licence": {
 				"kind": "spdx",
@@ -18645,8 +18842,17 @@ var catalogue_default = {
 			},
 			"citations": [{ "text": "Hu et al. (2020). Open Graph Benchmark: Datasets for Machine Learning on Graphs. NeurIPS." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (ogb-zip: format ogb-zip has a pipeline-specific parser with no declarative keepset form yet)"
+				"status": "fetchable",
+				"source": 1,
+				"archive": {
+					"kind": "zip",
+					"files": { "pattern": "[^/]+/raw/(?:num-node-list|num-node-dict|edge|num-edge-list|triplet-type-list|relations/[^/]+/(?:edge|num-edge-list))\\.csv\\.gz" },
+					"inner": { "kind": "gzip" }
+				},
+				"parser": {
+					"format": "ogb",
+					"encoding": "utf-8"
+				}
 			},
 			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
 			"expectedCounts": {
@@ -18690,7 +18896,7 @@ var catalogue_default = {
 			}],
 			"recipe": {
 				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (parquet: format parquet has a pipeline-specific parser with no declarative keepset form yet)"
+				"reason": "no download is in a form keepset reads yet (parquet: the download is a Hugging Face dataset repository whose citation table is thousands of Parquet files holding billions of rows, tens of gigabytes in all, more than a fetch can hold in memory, so no Parquet reader is added for it)"
 			},
 			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
 			"expectedCounts": {
@@ -23327,8 +23533,35 @@ var catalogue_default = {
 			},
 			"citations": [{ "text": "Szklarczyk et al. (2019). STRING: functional protein association networks. Nature Methods." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (biogrid-zip: format biogrid-zip has a pipeline-specific parser with no declarative keepset form yet)"
+				"status": "fetchable",
+				"source": 0,
+				"archive": {
+					"kind": "zip",
+					"member": { "pattern": "BIOGRID-ORGANISM-Homo_sapiens-[0-9.]+\\.tab3\\.txt" }
+				},
+				"parser": {
+					"format": "edge-list",
+					"encoding": "utf-8",
+					"delimiter": "tab",
+					"skipLines": 0,
+					"commentPrefixes": ["#"],
+					"sourceColumn": 3,
+					"targetColumn": 4,
+					"where": [
+						{
+							"column": 12,
+							"equals": "physical"
+						},
+						{
+							"column": 15,
+							"equals": "9606"
+						},
+						{
+							"column": 16,
+							"equals": "9606"
+						}
+					]
+				}
 			},
 			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
 			"expectedCounts": {
@@ -23756,8 +23989,18 @@ var catalogue_default = {
 			"licence": { "kind": "unrecorded" },
 			"citations": [{ "text": "Leskovec, Jure, Huttenlocher, Daniel, Kleinberg, Jon (2010). Signed Networks in Social Media. Proceedings of the SIGCHI Conference on Human Factors in Computing Systems." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (snap-signed: format snap-signed has a pipeline-specific parser with no declarative keepset form yet)"
+				"status": "fetchable",
+				"source": 0,
+				"archive": { "kind": "gzip" },
+				"parser": {
+					"format": "edge-list",
+					"encoding": "utf-8",
+					"delimiter": "tab",
+					"skipLines": 0,
+					"commentPrefixes": ["#"],
+					"sourceColumn": 0,
+					"targetColumn": 1
+				}
 			},
 			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
 			"expectedCounts": {
@@ -60338,8 +60581,18 @@ var catalogue_default = {
 			},
 			"citations": [{ "text": "Szklarczyk, Damian, Kirsch, Rebecca, Koutrouli, Mikaela, Nastou, Katerina, Mehryary, Farrokh, Hachilif, Radja, Annika, Gable, Fang, Tao, Doncheva, Nadezhda T., Letunic, Ivica, Bork, Peer, Jensen, Lars J., von Mering, Christian (2023). The STRING database in 2023: protein–protein association networks and functional enrichment analyses for any of 12 535 organisms. Nucleic Acids Research." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (string-ppi: format string-ppi has a pipeline-specific parser with no declarative keepset form yet)"
+				"status": "fetchable",
+				"source": 0,
+				"archive": { "kind": "gzip" },
+				"parser": {
+					"format": "edge-list",
+					"encoding": "utf-8",
+					"delimiter": "space",
+					"skipLines": 1,
+					"commentPrefixes": [],
+					"sourceColumn": 0,
+					"targetColumn": 1
+				}
 			},
 			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
 			"expectedCounts": {
@@ -60826,8 +61079,18 @@ var catalogue_default = {
 			},
 			"citations": [{ "text": "Barrat et al. (2004). The architecture of complex weighted networks. Proceedings of the National Academy of Sciences." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (csv: format csv has a pipeline-specific parser with no declarative keepset form yet)"
+				"status": "fetchable",
+				"source": 0,
+				"archive": { "kind": "none" },
+				"parser": {
+					"format": "edge-list",
+					"encoding": "utf-8",
+					"delimiter": "detect",
+					"skipLines": 0,
+					"commentPrefixes": ["#", "%"],
+					"sourceColumn": 2,
+					"targetColumn": 4
+				}
 			},
 			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
 			"expectedCounts": {
@@ -63378,18 +63641,39 @@ var catalogue_default = {
 			"sources": [{
 				"url": "https://www.wormatlas.org/images/NeuronConnect.xls",
 				"retrieved": "2026-04-20",
-				"status": "live"
+				"status": "dead",
+				"snapshot": {
+					"url": "https://web.archive.org/web/20260829213511/https://www.wormatlas.org/images/NeuronConnect.xls",
+					"timestamp": "20260829213511"
+				}
 			}],
 			"licence": { "kind": "unrecorded" },
 			"citations": [{ "text": "White, J. G., Southgate, E., Thomson, J. N., Brenner, S. (1986). The Structure of the Nervous System of the Nematode Caenorhabditis elegans. Phil. Trans. R. Soc. Lond. B 314, 1-340." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (xls: format xls has a pipeline-specific parser with no declarative keepset form yet)"
+				"status": "fetchable",
+				"source": 0,
+				"archive": {
+					"kind": "xls",
+					"sheet": "NeuronConnect.csv"
+				},
+				"parser": {
+					"format": "edge-list",
+					"encoding": "utf-8",
+					"delimiter": "comma",
+					"skipLines": 1,
+					"commentPrefixes": [],
+					"sourceColumn": 0,
+					"targetColumn": 1,
+					"keep": {
+						"column": 2,
+						"values": ["S", "Sp"]
+					}
+				}
 			},
 			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
 			"expectedCounts": {
-				"edges": 5233,
-				"nodes": 281
+				"edges": 2575,
+				"nodes": 279
 			},
 			"properties": {
 				"directed": true,
@@ -63412,18 +63696,39 @@ var catalogue_default = {
 			"sources": [{
 				"url": "https://www.wormatlas.org/images/NeuronConnect.xls",
 				"retrieved": "2026-04-20",
-				"status": "live"
+				"status": "dead",
+				"snapshot": {
+					"url": "https://web.archive.org/web/20260829213511/https://www.wormatlas.org/images/NeuronConnect.xls",
+					"timestamp": "20260829213511"
+				}
 			}],
 			"licence": { "kind": "unrecorded" },
 			"citations": [{ "text": "White, J. G., Southgate, E., Thomson, J. N., Brenner, S. (1986). The Structure of the Nervous System of the Nematode Caenorhabditis elegans. Phil. Trans. R. Soc. Lond. B 314, 1-340." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (xls: format xls has a pipeline-specific parser with no declarative keepset form yet)"
+				"status": "fetchable",
+				"source": 0,
+				"archive": {
+					"kind": "xls",
+					"sheet": "NeuronConnect.csv"
+				},
+				"parser": {
+					"format": "edge-list",
+					"encoding": "utf-8",
+					"delimiter": "comma",
+					"skipLines": 1,
+					"commentPrefixes": [],
+					"sourceColumn": 0,
+					"targetColumn": 1,
+					"keep": {
+						"column": 2,
+						"values": ["S", "Sp"]
+					}
+				}
 			},
 			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
 			"expectedCounts": {
-				"edges": 5233,
-				"nodes": 281
+				"edges": 2575,
+				"nodes": 279
 			},
 			"properties": {
 				"directed": false,
@@ -63446,18 +63751,39 @@ var catalogue_default = {
 			"sources": [{
 				"url": "https://www.wormatlas.org/images/NeuronConnect.xls",
 				"retrieved": "2026-04-20",
-				"status": "live"
+				"status": "dead",
+				"snapshot": {
+					"url": "https://web.archive.org/web/20260829213511/https://www.wormatlas.org/images/NeuronConnect.xls",
+					"timestamp": "20260829213511"
+				}
 			}],
 			"licence": { "kind": "unrecorded" },
 			"citations": [{ "text": "White, J. G., Southgate, E., Thomson, J. N., Brenner, S. (1986). The Structure of the Nervous System of the Nematode Caenorhabditis elegans. Phil. Trans. R. Soc. Lond. B 314, 1-340." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (xls: format xls has a pipeline-specific parser with no declarative keepset form yet)"
+				"status": "fetchable",
+				"source": 0,
+				"archive": {
+					"kind": "xls",
+					"sheet": "NeuronConnect.csv"
+				},
+				"parser": {
+					"format": "edge-list",
+					"encoding": "utf-8",
+					"delimiter": "comma",
+					"skipLines": 1,
+					"commentPrefixes": [],
+					"sourceColumn": 0,
+					"targetColumn": 1,
+					"keep": {
+						"column": 2,
+						"values": ["S", "Sp"]
+					}
+				}
 			},
 			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
 			"expectedCounts": {
-				"edges": 5233,
-				"nodes": 281
+				"edges": 2575,
+				"nodes": 279
 			},
 			"properties": {
 				"directed": true,
@@ -63480,18 +63806,40 @@ var catalogue_default = {
 			"sources": [{
 				"url": "https://www.wormatlas.org/images/NeuronConnect.xls",
 				"retrieved": "2026-04-20",
-				"status": "live"
+				"status": "dead",
+				"snapshot": {
+					"url": "https://web.archive.org/web/20260829213511/https://www.wormatlas.org/images/NeuronConnect.xls",
+					"timestamp": "20260829213511"
+				}
 			}],
 			"licence": { "kind": "unrecorded" },
 			"citations": [{ "text": "White, J. G., Southgate, E., Thomson, J. N., Brenner, S. (1986). The Structure of the Nervous System of the Nematode Caenorhabditis elegans. Phil. Trans. R. Soc. Lond. B 314, 1-340." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (xls: format xls has a pipeline-specific parser with no declarative keepset form yet)"
+				"status": "fetchable",
+				"source": 0,
+				"archive": {
+					"kind": "xls",
+					"sheet": "NeuronConnect.csv"
+				},
+				"parser": {
+					"format": "edge-list",
+					"encoding": "utf-8",
+					"delimiter": "comma",
+					"skipLines": 1,
+					"commentPrefixes": [],
+					"sourceColumn": 0,
+					"targetColumn": 1,
+					"keep": {
+						"column": 2,
+						"values": ["S", "Sp"]
+					},
+					"multiplicityColumn": 3
+				}
 			},
 			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
 			"expectedCounts": {
-				"edges": 5233,
-				"nodes": 281
+				"edges": 6394,
+				"nodes": 279
 			},
 			"properties": {
 				"directed": true,
@@ -63514,18 +63862,44 @@ var catalogue_default = {
 			"sources": [{
 				"url": "https://www.wormatlas.org/images/NeuronConnect.xls",
 				"retrieved": "2026-04-20",
-				"status": "live"
+				"status": "dead",
+				"snapshot": {
+					"url": "https://web.archive.org/web/20260829213511/https://www.wormatlas.org/images/NeuronConnect.xls",
+					"timestamp": "20260829213511"
+				}
 			}],
 			"licence": { "kind": "unrecorded" },
 			"citations": [{ "text": "White, J. G., Southgate, E., Thomson, J. N., Brenner, S. (1986). The Structure of the Nervous System of the Nematode Caenorhabditis elegans. Phil. Trans. R. Soc. Lond. B 314, 1-340." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (xls: format xls has a pipeline-specific parser with no declarative keepset form yet)"
+				"status": "fetchable",
+				"source": 0,
+				"archive": {
+					"kind": "xls",
+					"sheet": "NeuronConnect.csv"
+				},
+				"parser": {
+					"format": "edge-list",
+					"encoding": "utf-8",
+					"delimiter": "comma",
+					"skipLines": 1,
+					"commentPrefixes": [],
+					"sourceColumn": 0,
+					"targetColumn": 1,
+					"keep": {
+						"column": 2,
+						"values": [
+							"S",
+							"Sp",
+							"EJ",
+							"NMJ"
+						]
+					}
+				}
 			},
 			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
 			"expectedCounts": {
-				"edges": 6417,
-				"nodes": 283
+				"edges": 3759,
+				"nodes": 281
 			},
 			"properties": {
 				"directed": true,
@@ -63548,17 +63922,39 @@ var catalogue_default = {
 			"sources": [{
 				"url": "https://www.wormatlas.org/images/NeuronConnect.xls",
 				"retrieved": "2026-04-20",
-				"status": "live"
+				"status": "dead",
+				"snapshot": {
+					"url": "https://web.archive.org/web/20260829213511/https://www.wormatlas.org/images/NeuronConnect.xls",
+					"timestamp": "20260829213511"
+				}
 			}],
 			"licence": { "kind": "unrecorded" },
 			"citations": [{ "text": "White, J. G., Southgate, E., Thomson, J. N., Brenner, S. (1986). The Structure of the Nervous System of the Nematode Caenorhabditis elegans. Phil. Trans. R. Soc. Lond. B 314, 1-340." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (xls: format xls has a pipeline-specific parser with no declarative keepset form yet)"
+				"status": "fetchable",
+				"source": 0,
+				"archive": {
+					"kind": "xls",
+					"sheet": "NeuronConnect.csv"
+				},
+				"parser": {
+					"format": "edge-list",
+					"encoding": "utf-8",
+					"delimiter": "comma",
+					"skipLines": 1,
+					"commentPrefixes": [],
+					"sourceColumn": 0,
+					"targetColumn": 1,
+					"keep": {
+						"column": 2,
+						"values": ["EJ"]
+					},
+					"mirrored": true
+				}
 			},
 			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
 			"expectedCounts": {
-				"edges": 1031,
+				"edges": 517,
 				"nodes": 253
 			},
 			"properties": {
@@ -63591,12 +63987,25 @@ var catalogue_default = {
 			"licence": { "kind": "unrecorded" },
 			"citations": [{ "text": "Bumbarger, Daniel J., Sommer, Ralf J. (2013). System-wide rewiring underlies behavioral differences in predatory and bacterial-feeding nematodes. Cell 152(1), 109-119." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (bumbarger-consensus: format bumbarger-consensus has a pipeline-specific parser with no declarative keepset form yet)"
+				"status": "fetchable",
+				"source": 0,
+				"archive": {
+					"kind": "xlsx",
+					"sheet": "Sheet1"
+				},
+				"parser": {
+					"format": "edge-list",
+					"encoding": "utf-8",
+					"delimiter": "comma",
+					"skipLines": 2,
+					"commentPrefixes": [],
+					"sourceColumn": 0,
+					"targetColumn": 1
+				}
 			},
 			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
 			"expectedCounts": {
-				"edges": 533,
+				"edges": 78,
 				"nodes": 29
 			},
 			"properties": {
@@ -63626,7 +64035,7 @@ var catalogue_default = {
 			"citations": [{ "text": "Witvliet, Daniel, et al. (2020). Connectomes across development reveal principles of brain maturation. Nature." }],
 			"recipe": {
 				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (witvliet-json: format witvliet-json has a pipeline-specific parser with no declarative keepset form yet)"
+				"reason": "the graph joins the specimen's chemical synapse file with its gap junction file (Dataset1_gapjunctions.json beside it), and a recipe reads one download"
 			},
 			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
 			"expectedCounts": {
@@ -63659,8 +64068,13 @@ var catalogue_default = {
 			"licence": { "kind": "unrecorded" },
 			"citations": [{ "text": "Witvliet, Daniel, Mulcahy, Ben, Mitchell, James K., Meirovitch, Yaron, Bender, Andrew, Garrett, Miranda, Holmyard, Dianne, Schwarz, Kathryn, Ackerman, David G., Bhatt, Dhaval S., Bhatt, Bharti, Bhatt, Heena, Bhatt, Gauri, Bhatt, Rajni, Bhatt, Arushi, Bhatt, Tanya, Bhatt, Prateek, Bhatt, Sanskriti, Bhatt, Ananya, Bhatt, Aanya (2020). Connectomes across development reveal principles of brain maturation. Nature." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (witvliet-json: format witvliet-json has a pipeline-specific parser with no declarative keepset form yet)"
+				"status": "fetchable",
+				"source": 0,
+				"archive": { "kind": "none" },
+				"parser": {
+					"format": "witvliet-synapses",
+					"encoding": "utf-8"
+				}
 			},
 			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
 			"expectedCounts": {
@@ -63694,7 +64108,7 @@ var catalogue_default = {
 			"citations": [{ "text": "Witvliet, Daniel, et al. (2020). Connectomes across development reveal principles of brain maturation. Nature." }],
 			"recipe": {
 				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (witvliet-json: format witvliet-json has a pipeline-specific parser with no declarative keepset form yet)"
+				"reason": "the graph joins the specimen's chemical synapse file with its gap junction file (Dataset4_gapjunctions.json beside it), and a recipe reads one download"
 			},
 			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
 			"expectedCounts": {
@@ -63727,8 +64141,13 @@ var catalogue_default = {
 			"licence": { "kind": "unrecorded" },
 			"citations": [{ "text": "Witvliet, Daniel, et al. (2020). Connectomes across development reveal principles of brain maturation. Nature." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (witvliet-json: format witvliet-json has a pipeline-specific parser with no declarative keepset form yet)"
+				"status": "fetchable",
+				"source": 0,
+				"archive": { "kind": "none" },
+				"parser": {
+					"format": "witvliet-synapses",
+					"encoding": "utf-8"
+				}
 			},
 			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
 			"expectedCounts": {
@@ -63761,8 +64180,13 @@ var catalogue_default = {
 			"licence": { "kind": "unrecorded" },
 			"citations": [{ "text": "Witvliet, Daniel, et al. (2020). Connectomes across development reveal principles of brain maturation. Nature." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (witvliet-json: format witvliet-json has a pipeline-specific parser with no declarative keepset form yet)"
+				"status": "fetchable",
+				"source": 0,
+				"archive": { "kind": "none" },
+				"parser": {
+					"format": "witvliet-synapses",
+					"encoding": "utf-8"
+				}
 			},
 			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
 			"expectedCounts": {
@@ -63795,8 +64219,13 @@ var catalogue_default = {
 			"licence": { "kind": "unrecorded" },
 			"citations": [{ "text": "Witvliet, Daniel, et al. (2020). Connectomes across development reveal principles of brain maturation. Nature." }],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "no download is in a form keepset reads yet (witvliet-json: format witvliet-json has a pipeline-specific parser with no declarative keepset form yet)"
+				"status": "fetchable",
+				"source": 0,
+				"archive": { "kind": "none" },
+				"parser": {
+					"format": "witvliet-synapses",
+					"encoding": "utf-8"
+				}
 			},
 			"crosswalk": { "file": "crosswalks/graph-v1/topology.json" },
 			"expectedCounts": {