keepset 0.19.0 → 0.21.0

package/dist/{bundled-8oHQPxcd.js → bundled-NjZZ73vT.js}

@@ -410,7 +410,7 @@ const CitationSchema = z.object({
 const RelativePathSchema = z.string().refine((path) => path.split("/").every((segment) => segment !== "" && segment !== "." && segment !== ".."), { message: "must be a relative path of non-empty segments with no '.' or '..'" });
 /** Which file of an archive to read: a member path, matched against a member's whole path or its trailing segments (so `net.gml` finds `net/net.gml`), or the member whose name ends with one of a list of extensions (a format can have several, such as Pajek's `.net` and `.paj`). Either must match exactly one member when the recipe runs; macOS resource-fork members (`__MACOSX/` and `._` files) never match. */
 const ArchiveMemberSchema = z.union([z.object({ path: RelativePathSchema }).strict(), z.object({ extensions: z.array(z.string().regex(/^\.[A-Za-z0-9][A-Za-z0-9.]*$/, { message: "must be a file extension such as .mtx" })).min(1) }).strict()]);
-/** How the downloaded bytes unpack into the one file the parser reads. */
+/** How the downloaded bytes unpack into the one file the parser reads. A workbook (`xlsx`) is read as the CSV of its named sheet, with dates as ISO 8601 text, for the `csv-table` parser. */
 const ArchiveSchema = z.discriminatedUnion("kind", [
 	z.object({ kind: z.literal("none") }).strict(),
 	z.object({ kind: z.literal("gzip") }).strict(),
@@ -425,6 +425,10 @@ const ArchiveSchema = z.discriminatedUnion("kind", [
 	z.object({
 		kind: z.literal("tar.gz"),
 		member: ArchiveMemberSchema
+	}).strict(),
+	z.object({
+		kind: z.literal("xlsx"),
+		sheet: z.string().min(1)
 	}).strict()
 ]);
 const ColumnSchema = z.int().min(0);
@@ -510,10 +514,13 @@ const ParserSchema = z.discriminatedUnion("format", [
 		path: ["dateColumns"]
 	})
 ]);
-/** Where a source is a paged query and not one file: an ArcGIS feature layer, whose query endpoint returns a limited number of features per request. The source URL is the layer's, the download reads every page in `orderBy` order and the parser reads the one GeoJSON collection they make. */
+/** Where a source is a paged query and not one file. An ArcGIS feature layer returns a limited number of features per request: the source URL is the layer's, the download reads every page in `orderBy` order and the parser reads the one GeoJSON collection they make. A Socrata resource endpoint (`/resource/<id>.csv`) is read `pageSize` rows at a time in the order of its row ids, each page a CSV with its own header, and the download joins them into the one CSV the parser reads, so no single response has to survive a long transfer. */
 const PagingSchema = z.discriminatedUnion("kind", [z.object({
 	kind: z.literal("arcgis-query"),
 	orderBy: z.string().regex(/^[A-Za-z_][A-Za-z0-9_]*$/, { message: "must be a field name of the layer" })
+}).strict(), z.object({
+	kind: z.literal("socrata-resource"),
+	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. */
 const RecipeSchema = z.discriminatedUnion("status", [z.object({
@@ -889,7 +896,7 @@ var catalogue_default = {
 		"id": "keepset",
 		"name": "keepset",
 		"description": "The keepset catalogue: datasets with machine-readable recipes that fetch each one and normalise it into its category's target shape.",
-		"version": "1.7.0",
+		"version": "1.9.0",
 		"repository": "https://github.com/Mearman/keepset",
 		"namespaceAliases": {
 			"networkrepository": ["nr"],
@@ -1091,10 +1098,70 @@ var catalogue_default = {
 			},
 			"citations": [],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "The CSV is about 132 MB and holds more than a million rows (a full count gave over 1.1 million), which is more than a recipe can read into memory."
+				"status": "fetchable",
+				"source": 1,
+				"archive": { "kind": "none" },
+				"parser": {
+					"format": "csv-table",
+					"encoding": "utf-8",
+					"delimiter": "comma",
+					"skipLines": 0,
+					"idColumn": null,
+					"numericColumns": [{
+						"column": "ExpiationAmount",
+						"factor": 1
+					}],
+					"columns": [
+						"PaidDate",
+						"OffenceDate",
+						"ExpiationAmount",
+						"OffenceType",
+						"Status"
+					]
+				}
+			},
+			"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[].PaidDate",
+						"to": "nodes[].closed"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].OffenceDate",
+						"to": "nodes[].opened"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].ExpiationAmount",
+						"to": "nodes[].prize"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].OffenceType",
+						"to": "nodes[].skill"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].Status",
+						"to": "nodes[].status"
+					}
+				],
+				"oneWay": []
 			},
-			"crosswalk": { "file": "crosswalks/or-v1/nodes.json" },
 			"expectedCounts": {},
 			"properties": { "surveyId": "or-79" }
 		},
@@ -3386,14 +3453,110 @@ var catalogue_default = {
 				"url": "https://data.cityofchicago.org/Administration-Finance/Ordinance-Violations/6br9-quuz",
 				"retrieved": "2026-10-19",
 				"status": "live"
+			}, {
+				"url": "https://data.cityofchicago.org/resource/6br9-quuz.csv",
+				"retrieved": "2026-10-19",
+				"status": "live"
 			}],
 			"licence": { "kind": "unrecorded" },
 			"citations": [],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "The table has 824,653 rows and the probe's first rows, with cells already truncated, average about 330 bytes, so the export would exceed the 256 MiB a recipe can read."
+				"status": "fetchable",
+				"source": 1,
+				"paging": {
+					"kind": "socrata-resource",
+					"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": "imposed_fine",
+							"factor": 1
+						}
+					],
+					"columns": [
+						"hearing_date",
+						"latitude",
+						"longitude",
+						"violation_date",
+						"imposed_fine",
+						"violation_description",
+						"case_disposition",
+						"ward"
+					]
+				}
+			},
+			"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[].hearing_date",
+						"to": "nodes[].deadline"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].latitude",
+						"to": "nodes[].lat"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].longitude",
+						"to": "nodes[].lon"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].violation_date",
+						"to": "nodes[].opened"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].imposed_fine",
+						"to": "nodes[].prize"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].violation_description",
+						"to": "nodes[].skill"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].case_disposition",
+						"to": "nodes[].status"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].ward",
+						"to": "nodes[].territory"
+					}
+				],
+				"oneWay": []
 			},
-			"crosswalk": { "file": "crosswalks/or-v1/nodes.json" },
 			"expectedCounts": {},
 			"properties": { "surveyId": "or-65" }
 		},
@@ -4862,7 +5025,7 @@ var catalogue_default = {
 				"retrieved": "2026-10-19",
 				"status": "live"
 			}, {
-				"url": "https://www.dallasopendata.com/resource/xy7j-y59g.csv?%24limit=1000000",
+				"url": "https://www.dallasopendata.com/resource/xy7j-y59g.csv",
 				"retrieved": "2026-10-19",
 				"status": "live"
 			}],
@@ -4874,6 +5037,10 @@ var catalogue_default = {
 			"recipe": {
 				"status": "fetchable",
 				"source": 1,
+				"paging": {
+					"kind": "socrata-resource",
+					"pageSize": 5e4
+				},
 				"archive": { "kind": "none" },
 				"parser": {
 					"format": "csv-table",
@@ -4955,7 +5122,7 @@ var catalogue_default = {
 				"retrieved": "2026-10-19",
 				"status": "live"
 			}, {
-				"url": "https://www.dallasopendata.com/resource/skju-bfp8.csv?%24limit=1000000",
+				"url": "https://www.dallasopendata.com/resource/skju-bfp8.csv",
 				"retrieved": "2026-10-19",
 				"status": "live"
 			}],
@@ -4964,6 +5131,10 @@ var catalogue_default = {
 			"recipe": {
 				"status": "fetchable",
 				"source": 1,
+				"paging": {
+					"kind": "socrata-resource",
+					"pageSize": 5e4
+				},
 				"archive": { "kind": "none" },
 				"parser": {
 					"format": "csv-table",
@@ -5191,6 +5362,10 @@ var catalogue_default = {
 				"url": "https://environment.data.gov.uk/dataset/9c7728fc-68e2-46e1-addb-63790b6b5313",
 				"retrieved": "2026-10-19",
 				"status": "live"
+			}, {
+				"url": "https://environment.data.gov.uk/api/file/download?fileDataSetId=e06036f5-7f41-46a3-93ff-fbd0fa1a83cc&fileName=Environment_Agency_Prosecutions.xlsx",
+				"retrieved": "2026-10-19",
+				"status": "live"
 			}],
 			"licence": {
 				"kind": "spdx",
@@ -5198,10 +5373,73 @@ var catalogue_default = {
 			},
 			"citations": [],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "The download is an xlsx workbook with an explanation sheet and a data sheet, and keepset has no spreadsheet parser yet."
+				"status": "fetchable",
+				"source": 1,
+				"archive": {
+					"kind": "xlsx",
+					"sheet": "Environment Agency Prosecutions"
+				},
+				"parser": {
+					"format": "csv-table",
+					"encoding": "utf-8",
+					"delimiter": "comma",
+					"skipLines": 0,
+					"idColumn": null,
+					"numericColumns": [{
+						"column": "Fine",
+						"factor": 1
+					}],
+					"columns": [
+						"Date_of_Action",
+						"Fine",
+						"Incident_Type",
+						"Verdict",
+						"Incident_Area"
+					]
+				}
+			},
+			"crosswalk": {
+				"source": "csv-table",
+				"target": "or/v1",
+				"rules": [
+					{
+						"op": "move",
+						"from": "meta",
+						"to": "meta"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].id",
+						"to": "nodes[].id"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].Date_of_Action",
+						"to": "nodes[].closed"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].Fine",
+						"to": "nodes[].prize"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].Incident_Type",
+						"to": "nodes[].skill"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].Verdict",
+						"to": "nodes[].status"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].Incident_Area",
+						"to": "nodes[].territory"
+					}
+				],
+				"oneWay": []
 			},
-			"crosswalk": { "file": "crosswalks/or-v1/nodes.json" },
 			"expectedCounts": {},
 			"properties": { "surveyId": "or-50" }
 		},
@@ -8683,10 +8921,73 @@ var catalogue_default = {
 			},
 			"citations": [],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "The 2009 to 2017 csv is 328,582,222 bytes, over the 256 MiB a recipe can read, and the later years are published as spreadsheets (xlsx)."
+				"status": "fetchable",
+				"source": 1,
+				"archive": { "kind": "none" },
+				"parser": {
+					"format": "csv-table",
+					"encoding": "utf-8",
+					"delimiter": "comma",
+					"skipLines": 0,
+					"idColumn": "IncidentNumber",
+					"numericColumns": [{
+						"column": "Notional_Cost",
+						"factor": 1
+					}, {
+						"column": "PumpMinutesRounded",
+						"factor": 60
+					}],
+					"columns": [
+						"PumpMinutesRounded",
+						"DateOfCall",
+						"Notional_Cost",
+						"IncidentGroup",
+						"IncGeo_BoroughName"
+					]
+				}
+			},
+			"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[].PumpMinutesRounded",
+						"to": "nodes[].duration"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].DateOfCall",
+						"to": "nodes[].opened"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].Notional_Cost",
+						"to": "nodes[].prize"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].IncidentGroup",
+						"to": "nodes[].skill"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].IncGeo_BoroughName",
+						"to": "nodes[].territory"
+					}
+				],
+				"oneWay": []
 			},
-			"crosswalk": { "file": "crosswalks/or-v1/nodes.json" },
 			"expectedCounts": {},
 			"properties": { "surveyId": "or-111" }
 		},
@@ -8752,7 +9053,7 @@ var catalogue_default = {
 				"retrieved": "2026-10-19",
 				"status": "live"
 			}, {
-				"url": "https://data.lacity.org/resource/2u8b-eyuu.csv?%24limit=1000000",
+				"url": "https://data.lacity.org/resource/2u8b-eyuu.csv",
 				"retrieved": "2026-10-19",
 				"status": "live"
 			}],
@@ -8761,6 +9062,10 @@ var catalogue_default = {
 			"recipe": {
 				"status": "fetchable",
 				"source": 1,
+				"paging": {
+					"kind": "socrata-resource",
+					"pageSize": 5e4
+				},
 				"archive": { "kind": "none" },
 				"parser": {
 					"format": "csv-table",
@@ -9337,7 +9642,7 @@ var catalogue_default = {
 			"citations": [],
 			"recipe": {
 				"status": "not-fetchable",
-				"reason": "The single CSV is about 1.44 GB, far more than the 256 MiB a recipe can read into memory."
+				"reason": "The single CSV is about 1.44 GB and was not fetched whole, so its rows are not counted and no recipe is given."
 			},
 			"crosswalk": { "file": "crosswalks/or-v1/nodes.json" },
 			"expectedCounts": {},
@@ -9437,7 +9742,7 @@ var catalogue_default = {
 			"citations": [],
 			"recipe": {
 				"status": "not-fetchable",
-				"reason": "The county-level file is 916897688 bytes, far over the 256 MiB a recipe can read, and the other files are larger or are zip and xlsx."
+				"reason": "The county-level file is 916,897,688 bytes and was not fetched whole, so its rows are not counted and no recipe is given, and the other files are larger or are zip and xlsx."
 			},
 			"crosswalk": { "file": "crosswalks/or-v1/nodes.json" },
 			"expectedCounts": {},
@@ -9586,7 +9891,7 @@ var catalogue_default = {
 				"retrieved": "2026-10-19",
 				"status": "live"
 			}, {
-				"url": "https://citydata.mesaaz.gov/resource/3wic-ufd2.csv?%24limit=1000000",
+				"url": "https://citydata.mesaaz.gov/resource/3wic-ufd2.csv",
 				"retrieved": "2026-10-19",
 				"status": "live"
 			}],
@@ -9595,6 +9900,10 @@ var catalogue_default = {
 			"recipe": {
 				"status": "fetchable",
 				"source": 1,
+				"paging": {
+					"kind": "socrata-resource",
+					"pageSize": 5e4
+				},
 				"archive": { "kind": "none" },
 				"parser": {
 					"format": "csv-table",
@@ -9709,10 +10018,83 @@ var catalogue_default = {
 			"licence": { "kind": "unrecorded" },
 			"citations": [],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "The table has 1,631,480 rows, more than a recipe can read."
+				"status": "fetchable",
+				"source": 1,
+				"paging": {
+					"kind": "socrata-resource",
+					"pageSize": 5e4
+				},
+				"archive": { "kind": "none" },
+				"parser": {
+					"format": "csv-table",
+					"encoding": "utf-8",
+					"delimiter": "comma",
+					"skipLines": 0,
+					"idColumn": "event_number",
+					"numericColumns": [{
+						"column": "response_time_seconds",
+						"factor": 1
+					}, {
+						"column": "on_scene_time_seconds",
+						"factor": 1
+					}],
+					"columns": [
+						"clear_date_time",
+						"on_scene_time_seconds",
+						"received_date_time",
+						"initial_case_type",
+						"district",
+						"response_time_seconds"
+					]
+				}
+			},
+			"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[].clear_date_time",
+						"to": "nodes[].closed"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].on_scene_time_seconds",
+						"to": "nodes[].duration"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].received_date_time",
+						"to": "nodes[].opened"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].initial_case_type",
+						"to": "nodes[].skill"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].district",
+						"to": "nodes[].territory"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].response_time_seconds",
+						"to": "nodes[].travelTime"
+					}
+				],
+				"oneWay": []
 			},
-			"crosswalk": { "file": "crosswalks/or-v1/nodes.json" },
 			"expectedCounts": {},
 			"properties": { "surveyId": "or-109" }
 		},
@@ -9738,7 +10120,7 @@ var catalogue_default = {
 				"retrieved": "2026-10-19",
 				"status": "live"
 			}, {
-				"url": "https://citydata.mesaaz.gov/resource/ay68-xuca.csv?%24limit=1000000",
+				"url": "https://citydata.mesaaz.gov/resource/ay68-xuca.csv",
 				"retrieved": "2026-10-19",
 				"status": "live"
 			}],
@@ -9747,6 +10129,10 @@ var catalogue_default = {
 			"recipe": {
 				"status": "fetchable",
 				"source": 1,
+				"paging": {
+					"kind": "socrata-resource",
+					"pageSize": 5e4
+				},
 				"archive": { "kind": "none" },
 				"parser": {
 					"format": "csv-table",
@@ -9861,14 +10247,88 @@ var catalogue_default = {
 				"url": "https://citydata.mesaaz.gov/Water-Resources/Water-Resources-Work-Orders-Public-View/7rqv-jcr4",
 				"retrieved": "2026-10-19",
 				"status": "live"
+			}, {
+				"url": "https://citydata.mesaaz.gov/resource/7rqv-jcr4.csv",
+				"retrieved": "2026-10-19",
+				"status": "live"
 			}],
 			"licence": { "kind": "unrecorded" },
 			"citations": [],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "The table has 934800 rows of more than 100 columns, and the sample rows are about a kilobyte each, so the download is far larger than the 256 MiB a recipe can read into memory."
+				"status": "fetchable",
+				"source": 1,
+				"paging": {
+					"kind": "socrata-resource",
+					"pageSize": 5e4
+				},
+				"archive": { "kind": "none" },
+				"parser": {
+					"format": "csv-table",
+					"encoding": "utf-8",
+					"delimiter": "comma",
+					"skipLines": 0,
+					"idColumn": null,
+					"numericColumns": [{
+						"column": "work_order_cost",
+						"factor": 1
+					}],
+					"columns": [
+						"work_order_close_date",
+						"projected_finish_date",
+						"initiated_date",
+						"work_order_cost",
+						"work_order_category",
+						"status"
+					]
+				}
+			},
+			"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[].work_order_close_date",
+						"to": "nodes[].closed"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].projected_finish_date",
+						"to": "nodes[].deadline"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].initiated_date",
+						"to": "nodes[].opened"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].work_order_cost",
+						"to": "nodes[].prize"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].work_order_category",
+						"to": "nodes[].skill"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].status",
+						"to": "nodes[].status"
+					}
+				],
+				"oneWay": []
 			},
-			"crosswalk": { "file": "crosswalks/or-v1/nodes.json" },
 			"expectedCounts": {},
 			"properties": { "surveyId": "or-13" }
 		},
@@ -9940,7 +10400,7 @@ var catalogue_default = {
 				"retrieved": "2026-10-19",
 				"status": "live"
 			}, {
-				"url": "https://data.montgomerycountymd.gov/resource/bw2r-araf.csv?%24limit=1000000",
+				"url": "https://data.montgomerycountymd.gov/resource/bw2r-araf.csv",
 				"retrieved": "2026-10-19",
 				"status": "live"
 			}],
@@ -9953,6 +10413,10 @@ var catalogue_default = {
 			"recipe": {
 				"status": "fetchable",
 				"source": 1,
+				"paging": {
+					"kind": "socrata-resource",
+					"pageSize": 5e4
+				},
 				"archive": { "kind": "none" },
 				"parser": {
 					"format": "csv-table",
@@ -13494,7 +13958,7 @@ var catalogue_default = {
 				"retrieved": "2026-10-19",
 				"status": "live"
 			}, {
-				"url": "https://data.nola.gov/resource/44ct-56tr.csv?%24limit=1000000",
+				"url": "https://data.nola.gov/resource/44ct-56tr.csv",
 				"retrieved": "2026-10-19",
 				"status": "live"
 			}],
@@ -13506,6 +13970,10 @@ var catalogue_default = {
 			"recipe": {
 				"status": "fetchable",
 				"source": 1,
+				"paging": {
+					"kind": "socrata-resource",
+					"pageSize": 5e4
+				},
 				"archive": { "kind": "none" },
 				"parser": {
 					"format": "csv-table",
@@ -13906,7 +14374,7 @@ var catalogue_default = {
 				"retrieved": "2026-10-19",
 				"status": "live"
 			}, {
-				"url": "https://data.norfolk.gov/resource/qzfe-wj25.csv?%24limit=1000000",
+				"url": "https://data.norfolk.gov/resource/qzfe-wj25.csv",
 				"retrieved": "2026-10-19",
 				"status": "live"
 			}],
@@ -13915,6 +14383,10 @@ var catalogue_default = {
 			"recipe": {
 				"status": "fetchable",
 				"source": 1,
+				"paging": {
+					"kind": "socrata-resource",
+					"pageSize": 5e4
+				},
 				"archive": { "kind": "none" },
 				"parser": {
 					"format": "csv-table",
@@ -14480,7 +14952,7 @@ var catalogue_default = {
 			"citations": [],
 			"recipe": {
 				"status": "not-fetchable",
-				"reason": "The table has 22,844,087 rows, more than a recipe can read."
+				"reason": "The table has 22,844,087 rows, so even one mapped column and the id hold more cells than a fetch can hold in memory."
 			},
 			"crosswalk": { "file": "crosswalks/or-v1/nodes.json" },
 			"expectedCounts": {},
@@ -14510,7 +14982,7 @@ var catalogue_default = {
 			"citations": [],
 			"recipe": {
 				"status": "not-fetchable",
-				"reason": "The CSV has 2716297 rows, which is more than a recipe can read into memory."
+				"reason": "The table has 2,716,297 rows, so a mapping of more than three columns plus the id holds more cells than a fetch can hold in memory, and three columns would carry too little of what the table offers."
 			},
 			"crosswalk": { "file": "crosswalks/or-v1/nodes.json" },
 			"expectedCounts": {},
@@ -14536,14 +15008,79 @@ var catalogue_default = {
 				"url": "https://data.cityofnewyork.us/Housing-Development/DOB-NOW-Electrical-Permit-Applications/dm9a-ab7w",
 				"retrieved": "2026-10-19",
 				"status": "live"
+			}, {
+				"url": "https://data.cityofnewyork.us/resource/dm9a-ab7w.csv",
+				"retrieved": "2026-10-19",
+				"status": "live"
 			}],
 			"licence": { "kind": "unrecorded" },
 			"citations": [],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "The table has 594449 rows of about 80 wide columns, roughly 900 bytes a row in a sampled export, so the download is well over the 256 MiB a recipe can read."
+				"status": "fetchable",
+				"source": 1,
+				"paging": {
+					"kind": "socrata-resource",
+					"pageSize": 5e4
+				},
+				"archive": { "kind": "none" },
+				"parser": {
+					"format": "csv-table",
+					"encoding": "utf-8",
+					"delimiter": "comma",
+					"skipLines": 0,
+					"idColumn": "job_filing_number",
+					"numericColumns": [],
+					"columns": [
+						"completion_date",
+						"filing_date",
+						"filing_type",
+						"filing_status",
+						"borough"
+					]
+				}
+			},
+			"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[].completion_date",
+						"to": "nodes[].closed"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].filing_date",
+						"to": "nodes[].opened"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].filing_type",
+						"to": "nodes[].skill"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].filing_status",
+						"to": "nodes[].status"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].borough",
+						"to": "nodes[].territory"
+					}
+				],
+				"oneWay": []
 			},
-			"crosswalk": { "file": "crosswalks/or-v1/nodes.json" },
 			"expectedCounts": {},
 			"properties": { "surveyId": "or-88" }
 		},
@@ -14875,7 +15412,7 @@ var catalogue_default = {
 			"citations": [],
 			"recipe": {
 				"status": "not-fetchable",
-				"reason": "The CSV has 3990985 rows, which is more than a recipe can read into memory."
+				"reason": "The table has 3,990,985 rows, so a mapping of more than two columns plus the id holds more cells than a fetch can hold in memory, and two columns would carry too little of what the table offers."
 			},
 			"crosswalk": { "file": "crosswalks/or-v1/nodes.json" },
 			"expectedCounts": {},
@@ -14902,10 +15439,74 @@ var catalogue_default = {
 			"licence": { "kind": "unrecorded" },
 			"citations": [],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "The table has 1,539,045 rows, more than a recipe can read."
+				"status": "fetchable",
+				"source": 1,
+				"paging": {
+					"kind": "socrata-resource",
+					"pageSize": 5e4
+				},
+				"archive": { "kind": "none" },
+				"parser": {
+					"format": "csv-table",
+					"encoding": "utf-8",
+					"delimiter": "comma",
+					"skipLines": 0,
+					"idColumn": null,
+					"numericColumns": [{
+						"column": "judgment_amount",
+						"factor": 1
+					}],
+					"columns": [
+						"redemption_date",
+						"boot_date",
+						"judgment_amount",
+						"type",
+						"case_status"
+					]
+				}
+			},
+			"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[].redemption_date",
+						"to": "nodes[].closed"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].boot_date",
+						"to": "nodes[].opened"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].judgment_amount",
+						"to": "nodes[].prize"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].type",
+						"to": "nodes[].skill"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].case_status",
+						"to": "nodes[].status"
+					}
+				],
+				"oneWay": []
 			},
-			"crosswalk": { "file": "crosswalks/or-v1/nodes.json" },
 			"expectedCounts": {},
 			"properties": { "surveyId": "or-101" }
 		},
@@ -15005,7 +15606,7 @@ var catalogue_default = {
 				"retrieved": "2026-10-19",
 				"status": "live"
 			}, {
-				"url": "https://data.cityofnewyork.us/resource/6z8x-wfk4.csv?%24limit=1000000",
+				"url": "https://data.cityofnewyork.us/resource/6z8x-wfk4.csv",
 				"retrieved": "2026-10-19",
 				"status": "live"
 			}],
@@ -15014,6 +15615,10 @@ var catalogue_default = {
 			"recipe": {
 				"status": "fetchable",
 				"source": 1,
+				"paging": {
+					"kind": "socrata-resource",
+					"pageSize": 5e4
+				},
 				"archive": { "kind": "none" },
 				"parser": {
 					"format": "csv-table",
@@ -15105,7 +15710,7 @@ var catalogue_default = {
 			"citations": [],
 			"recipe": {
 				"status": "not-fetchable",
-				"reason": "The table has 30,389,767 rows, more than a recipe can read."
+				"reason": "The table has 30,389,767 rows, so even one mapped column and the id hold more cells than a fetch can hold in memory."
 			},
 			"crosswalk": { "file": "crosswalks/or-v1/nodes.json" },
 			"expectedCounts": {},
@@ -15219,14 +15824,91 @@ var catalogue_default = {
 				"url": "https://data.cityofnewyork.us/Environment/Forestry-Work-Orders/bdjm-n7q4",
 				"retrieved": "2026-10-19",
 				"status": "live"
+			}, {
+				"url": "https://data.cityofnewyork.us/resource/bdjm-n7q4.csv",
+				"retrieved": "2026-10-19",
+				"status": "live"
 			}],
 			"licence": { "kind": "unrecorded" },
 			"citations": [],
 			"recipe": {
-				"status": "not-fetchable",
-				"reason": "The table has 1561796 rows, more than a recipe can read."
+				"status": "fetchable",
+				"source": 1,
+				"paging": {
+					"kind": "socrata-resource",
+					"pageSize": 5e4
+				},
+				"archive": { "kind": "none" },
+				"parser": {
+					"format": "csv-table",
+					"encoding": "utf-8",
+					"delimiter": "comma",
+					"skipLines": 0,
+					"idColumn": "objectid",
+					"numericColumns": [{
+						"column": "latitude",
+						"factor": 1
+					}, {
+						"column": "longitude",
+						"factor": 1
+					}],
+					"columns": [
+						"closeddate",
+						"latitude",
+						"longitude",
+						"createddate",
+						"wotype",
+						"wostatus"
+					]
+				}
+			},
+			"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[].closeddate",
+						"to": "nodes[].closed"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].latitude",
+						"to": "nodes[].lat"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].longitude",
+						"to": "nodes[].lon"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].createddate",
+						"to": "nodes[].opened"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].wotype",
+						"to": "nodes[].skill"
+					},
+					{
+						"op": "move",
+						"from": "nodes[].wostatus",
+						"to": "nodes[].status"
+					}
+				],
+				"oneWay": []
 			},
-			"crosswalk": { "file": "crosswalks/or-v1/nodes.json" },
 			"expectedCounts": {},
 			"properties": { "surveyId": "or-15" }
 		},
@@ -15252,7 +15934,7 @@ var catalogue_default = {
 			"citations": [],
 			"recipe": {
 				"status": "not-fetchable",
-				"reason": "The table has 11,324,217 rows, more than a recipe can read into memory."
+				"reason": "The table has 11,324,217 rows, so a mapping of even one column and the id holds more cells than a fetch can hold in memory."
 			},
 			"crosswalk": { "file": "crosswalks/or-v1/nodes.json" },
 			"expectedCounts": {},
@@ -15401,7 +16083,7 @@ var catalogue_default = {
 			"citations": [],
 			"recipe": {
 				"status": "not-fetchable",
-				"reason": "The table has 10,484,258 rows, more than a recipe can read."
+				"reason": "The table has 10,484,258 rows, so a mapping of even two columns and the id holds more cells than a fetch can hold in memory."
 			},
 			"crosswalk": { "file": "crosswalks/or-v1/nodes.json" },
 			"expectedCounts": {},
@@ -15429,7 +16111,7 @@ var catalogue_default = {
 			"citations": [],
 			"recipe": {
 				"status": "not-fetchable",
-				"reason": "The table has 22,151,329 rows, more than a recipe can read into memory."
+				"reason": "The table has 22,151,329 rows, so even one mapped column and the id hold more cells than a fetch can hold in memory."
 			},
 			"crosswalk": { "file": "crosswalks/or-v1/nodes.json" },
 			"expectedCounts": {},
@@ -15454,7 +16136,7 @@ var catalogue_default = {
 				"retrieved": "2026-10-19",
 				"status": "live"
 			}, {
-				"url": "https://data.cityofnewyork.us/resource/xnfm-u3k5.csv?%24limit=1000000",
+				"url": "https://data.cityofnewyork.us/resource/xnfm-u3k5.csv",
 				"retrieved": "2026-10-19",
 				"status": "live"
 			}],
@@ -15463,6 +16145,10 @@ var catalogue_default = {
 			"recipe": {
 				"status": "fetchable",
 				"source": 1,
+				"paging": {
+					"kind": "socrata-resource",
+					"pageSize": 5e4
+				},
 				"archive": { "kind": "none" },
 				"parser": {
 					"format": "csv-table",
@@ -55134,7 +55820,7 @@ var catalogue_default = {
 				"retrieved": "2026-10-19",
 				"status": "live"
 			}, {
-				"url": "https://data.wa.gov/resource/m8qx-ubtq.csv?%24limit=1000000",
+				"url": "https://data.wa.gov/resource/m8qx-ubtq.csv",
 				"retrieved": "2026-10-19",
 				"status": "live"
 			}],
@@ -55146,6 +55832,10 @@ var catalogue_default = {
 			"recipe": {
 				"status": "fetchable",
 				"source": 1,
+				"paging": {
+					"kind": "socrata-resource",
+					"pageSize": 5e4
+				},
 				"archive": { "kind": "none" },
 				"parser": {
 					"format": "csv-table",