keepset 0.34.0 → 0.36.0

package/dist/{categories-DUG7URRd.d.ts → categories-D9r42M9E.d.ts}

@@ -74,7 +74,7 @@ declare const ArchiveMemberSchema: z.ZodUnion<readonly [z.ZodObject<{
   pattern: z.ZodString;
 }, z.core.$strict>]>;
 type ArchiveMember = z.infer<typeof ArchiveMemberSchema>;
-/** An archive a collection is read from: every file a selector matches, at least one. */
+/** An archive a collection is read from: every file a selector matches, at least one. With `inner` of kind `xlsx`, every matched member is a workbook and each of its sheets, in the workbook's order, is one file of the collection: the sheet's CSV, at the path of the member and the sheet's name joined by `/`, for an instance format laid out on a sheet. `sheets` is a regular expression a sheet's whole name must match for the sheet to be read (every sheet when it is absent), and it must match at least one sheet of every workbook. */
 declare const CollectionArchiveSchema: z.ZodObject<{
   kind: z.ZodEnum<{
     zip: "zip";
@@ -89,8 +89,12 @@ declare const CollectionArchiveSchema: z.ZodObject<{
   }, z.core.$strict>, z.ZodObject<{
     pattern: z.ZodString;
   }, z.core.$strict>]>;
+  inner: z.ZodOptional<z.ZodObject<{
+    kind: z.ZodLiteral<"xlsx">;
+    sheets: z.ZodOptional<z.ZodString>;
+  }, z.core.$strict>>;
 }, z.core.$strict>;
-/** How the downloaded bytes unpack into the file the parser reads, or for a collection the files it reads one by one. A `members` selector gives every member it matches, at least one, in path order. `gzip` and `bzip2` are one compressed file, and `tar.gz` and `tar.bz2` a tar archive compressed with them. A member that is an archive in its turn (a contest bundle that ships its problems as a zip inside the zip) is unpacked by `inner`. A workbook (`xlsx`) is read as the CSV of its named sheet, with dates as ISO 8601 text, for the `csv-table` parser. */
+/** How the downloaded bytes unpack into the file the parser reads, or for a collection the files it reads one by one. A `members` selector gives every member it matches, at least one, in path order. `gzip` and `bzip2` are one compressed file, and `tar.gz` and `tar.bz2` a tar archive compressed with them. A member that is an archive in its turn (a contest bundle that ships its problems as a zip inside the zip) is unpacked by `inner`. A workbook (`xlsx`) is read as the CSV of its named sheet, with dates as ISO 8601 text, for the `csv-table` parser. A point shapefile (`shapefile`) is a zip whose `member` selects the `.shp`, read with the `.dbf`, `.prj` and `.cpg` of the same name beside it as the CSV of its attribute table with each point's stored coordinates and its WGS84 position, for the `csv-table` parser. */
 declare const ArchiveSchema: z.ZodUnion<readonly [z.ZodObject<{
   kind: z.ZodLiteral<"none">;
 }, z.core.$strict>, z.ZodObject<{
@@ -142,9 +146,22 @@ declare const ArchiveSchema: z.ZodUnion<readonly [z.ZodObject<{
   }, z.core.$strict>, z.ZodObject<{
     pattern: z.ZodString;
   }, z.core.$strict>]>;
+  inner: z.ZodOptional<z.ZodObject<{
+    kind: z.ZodLiteral<"xlsx">;
+    sheets: z.ZodOptional<z.ZodString>;
+  }, z.core.$strict>>;
 }, z.core.$strict>, z.ZodObject<{
   kind: z.ZodLiteral<"xlsx">;
   sheet: z.ZodString;
+}, z.core.$strict>, z.ZodObject<{
+  kind: z.ZodLiteral<"shapefile">;
+  member: z.ZodUnion<readonly [z.ZodObject<{
+    path: z.ZodString;
+  }, z.core.$strict>, z.ZodObject<{
+    extensions: z.ZodArray<z.ZodString>;
+  }, z.core.$strict>, z.ZodObject<{
+    pattern: z.ZodString;
+  }, z.core.$strict>]>;
 }, z.core.$strict>]>;
 type Archive = z.infer<typeof ArchiveSchema>;
 /** An archive that gives the one file a document is read from. */
@@ -259,6 +276,9 @@ declare const ParserSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
 }, z.core.$strict>, z.ZodObject<{
   format: z.ZodLiteral<"vrp-rep">;
   encoding: z.ZodLiteral<"utf-8">;
+}, z.core.$strict>, z.ZodObject<{
+  format: z.ZodLiteral<"hhcrsp">;
+  encoding: z.ZodLiteral<"utf-8">;
 }, z.core.$strict>, z.ZodObject<{
   format: z.ZodLiteral<"csv-table">;
   encoding: z.ZodEnum<{
@@ -358,9 +378,22 @@ declare const RecipeSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
     }, z.core.$strict>, z.ZodObject<{
       pattern: z.ZodString;
     }, z.core.$strict>]>;
+    inner: z.ZodOptional<z.ZodObject<{
+      kind: z.ZodLiteral<"xlsx">;
+      sheets: z.ZodOptional<z.ZodString>;
+    }, z.core.$strict>>;
   }, z.core.$strict>, z.ZodObject<{
     kind: z.ZodLiteral<"xlsx">;
     sheet: z.ZodString;
+  }, z.core.$strict>, z.ZodObject<{
+    kind: z.ZodLiteral<"shapefile">;
+    member: z.ZodUnion<readonly [z.ZodObject<{
+      path: z.ZodString;
+    }, z.core.$strict>, z.ZodObject<{
+      extensions: z.ZodArray<z.ZodString>;
+    }, z.core.$strict>, z.ZodObject<{
+      pattern: z.ZodString;
+    }, z.core.$strict>]>;
   }, z.core.$strict>]>;
   parser: z.ZodDiscriminatedUnion<[z.ZodObject<{
     format: z.ZodLiteral<"edge-list">;
@@ -465,6 +498,9 @@ declare const RecipeSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
   }, z.core.$strict>, z.ZodObject<{
     format: z.ZodLiteral<"vrp-rep">;
     encoding: z.ZodLiteral<"utf-8">;
+  }, z.core.$strict>, z.ZodObject<{
+    format: z.ZodLiteral<"hhcrsp">;
+    encoding: z.ZodLiteral<"utf-8">;
   }, z.core.$strict>, z.ZodObject<{
     format: z.ZodLiteral<"csv-table">;
     encoding: z.ZodEnum<{
@@ -619,9 +655,22 @@ declare const EntrySchema: z.ZodObject<{
       }, z.core.$strict>, z.ZodObject<{
         pattern: z.ZodString;
       }, z.core.$strict>]>;
+      inner: z.ZodOptional<z.ZodObject<{
+        kind: z.ZodLiteral<"xlsx">;
+        sheets: z.ZodOptional<z.ZodString>;
+      }, z.core.$strict>>;
     }, z.core.$strict>, z.ZodObject<{
       kind: z.ZodLiteral<"xlsx">;
       sheet: z.ZodString;
+    }, z.core.$strict>, z.ZodObject<{
+      kind: z.ZodLiteral<"shapefile">;
+      member: z.ZodUnion<readonly [z.ZodObject<{
+        path: z.ZodString;
+      }, z.core.$strict>, z.ZodObject<{
+        extensions: z.ZodArray<z.ZodString>;
+      }, z.core.$strict>, z.ZodObject<{
+        pattern: z.ZodString;
+      }, z.core.$strict>]>;
     }, z.core.$strict>]>;
     parser: z.ZodDiscriminatedUnion<[z.ZodObject<{
       format: z.ZodLiteral<"edge-list">;
@@ -726,6 +775,9 @@ declare const EntrySchema: z.ZodObject<{
     }, z.core.$strict>, z.ZodObject<{
       format: z.ZodLiteral<"vrp-rep">;
       encoding: z.ZodLiteral<"utf-8">;
+    }, z.core.$strict>, z.ZodObject<{
+      format: z.ZodLiteral<"hhcrsp">;
+      encoding: z.ZodLiteral<"utf-8">;
     }, z.core.$strict>, z.ZodObject<{
       format: z.ZodLiteral<"csv-table">;
       encoding: z.ZodEnum<{
@@ -809,6 +861,10 @@ declare const EntrySchema: z.ZodObject<{
         } | {
           pattern: string;
         };
+        inner?: {
+          kind: "xlsx";
+          sheets?: string | undefined;
+        } | undefined;
       } | {
         kind: "none";
       } | {
@@ -839,6 +895,15 @@ declare const EntrySchema: z.ZodObject<{
       } | {
         kind: "xlsx";
         sheet: string;
+      } | {
+        kind: "shapefile";
+        member: {
+          path: string;
+        } | {
+          extensions: string[];
+        } | {
+          pattern: string;
+        };
       };
       parser: {
         format: "edge-list";
@@ -919,6 +984,9 @@ declare const EntrySchema: z.ZodObject<{
       } | {
         format: "vrp-rep";
         encoding: "utf-8";
+      } | {
+        format: "hhcrsp";
+        encoding: "utf-8";
       };
       paging?: {
         kind: "arcgis-query";
@@ -1149,9 +1217,22 @@ declare const CatalogueIndexSchema: z.ZodObject<{
         }, z.core.$strict>, z.ZodObject<{
           pattern: z.ZodString;
         }, z.core.$strict>]>;
+        inner: z.ZodOptional<z.ZodObject<{
+          kind: z.ZodLiteral<"xlsx">;
+          sheets: z.ZodOptional<z.ZodString>;
+        }, z.core.$strict>>;
       }, z.core.$strict>, z.ZodObject<{
         kind: z.ZodLiteral<"xlsx">;
         sheet: z.ZodString;
+      }, z.core.$strict>, z.ZodObject<{
+        kind: z.ZodLiteral<"shapefile">;
+        member: z.ZodUnion<readonly [z.ZodObject<{
+          path: z.ZodString;
+        }, z.core.$strict>, z.ZodObject<{
+          extensions: z.ZodArray<z.ZodString>;
+        }, z.core.$strict>, z.ZodObject<{
+          pattern: z.ZodString;
+        }, z.core.$strict>]>;
       }, z.core.$strict>]>;
       parser: z.ZodDiscriminatedUnion<[z.ZodObject<{
         format: z.ZodLiteral<"edge-list">;
@@ -1256,6 +1337,9 @@ declare const CatalogueIndexSchema: z.ZodObject<{
       }, z.core.$strict>, z.ZodObject<{
         format: z.ZodLiteral<"vrp-rep">;
         encoding: z.ZodLiteral<"utf-8">;
+      }, z.core.$strict>, z.ZodObject<{
+        format: z.ZodLiteral<"hhcrsp">;
+        encoding: z.ZodLiteral<"utf-8">;
       }, z.core.$strict>, z.ZodObject<{
         format: z.ZodLiteral<"csv-table">;
         encoding: z.ZodEnum<{
@@ -1339,6 +1423,10 @@ declare const CatalogueIndexSchema: z.ZodObject<{
           } | {
             pattern: string;
           };
+          inner?: {
+            kind: "xlsx";
+            sheets?: string | undefined;
+          } | undefined;
         } | {
           kind: "none";
         } | {
@@ -1369,6 +1457,15 @@ declare const CatalogueIndexSchema: z.ZodObject<{
         } | {
           kind: "xlsx";
           sheet: string;
+        } | {
+          kind: "shapefile";
+          member: {
+            path: string;
+          } | {
+            extensions: string[];
+          } | {
+            pattern: string;
+          };
         };
         parser: {
           format: "edge-list";
@@ -1449,6 +1546,9 @@ declare const CatalogueIndexSchema: z.ZodObject<{
         } | {
           format: "vrp-rep";
           encoding: "utf-8";
+        } | {
+          format: "hhcrsp";
+          encoding: "utf-8";
         };
         paging?: {
           kind: "arcgis-query";
@@ -1536,6 +1636,10 @@ declare const CatalogueIndexSchema: z.ZodObject<{
           } | {
             pattern: string;
           };
+          inner?: {
+            kind: "xlsx";
+            sheets?: string | undefined;
+          } | undefined;
         } | {
           kind: "none";
         } | {
@@ -1566,6 +1670,15 @@ declare const CatalogueIndexSchema: z.ZodObject<{
         } | {
           kind: "xlsx";
           sheet: string;
+        } | {
+          kind: "shapefile";
+          member: {
+            path: string;
+          } | {
+            extensions: string[];
+          } | {
+            pattern: string;
+          };
         };
         parser: {
           format: "edge-list";
@@ -1646,6 +1759,9 @@ declare const CatalogueIndexSchema: z.ZodObject<{
         } | {
           format: "vrp-rep";
           encoding: "utf-8";
+        } | {
+          format: "hhcrsp";
+          encoding: "utf-8";
         };
         paging?: {
           kind: "arcgis-query";

package/dist/index.d.ts

@@ -1,4 +1,4 @@
-import { $ as CrosswalkReference, A as Catalogue, B as ManifestSchema, C as JsonScalarSchema, Ct as waybackUrl, D as GraphNodeSchema, E as GraphNode, F as NamespaceNode, G as ArchiveMember, H as parseManifest, I as createCatalogue, J as Citation, K as ArchiveMemberSchema, L as Lineage, M as CatalogueIndexSchema, N as Dataset, O as GraphV1, P as DatasetQuery, Q as ColumnNameSchema, R as LineageSchema, S as JsonScalar, St as parseEntry, T as GraphEdgeSchema, U as AliasSchema, V as SemVerSchema, W as Archive, X as CollectionArchive, Y as CitationSchema, Z as CollectionArchiveSchema, _ as TasksV1, _t as SnapshotSchema, a as CategoryTargets, at as IdSchema, b as Instance, bt as SubjectSchema, c as countTarget, ct as Namespace, d as getCollectionTarget, dt as ParserSchema, et as CrosswalkReferenceSchema, f as getTarget, ft as RESERVED_META_KEYS, g as TaskSchema, gt as Snapshot, h as Task, ht as RelativePathSchema, i as CategoryTarget, it as HttpUrlSchema, j as CatalogueIndex, k as GraphV1Schema, l as countedKeys, lt as NamespaceSchema, m as listCategories, mt as RecipeSchema, n as CategoryId, nt as Entry, o as CollectionTarget, ot as Licence, p as kindOf, pt as Recipe, q as ArchiveSchema, r as CategoryIdSchema, rt as EntrySchema, s as CountedKey, st as LicenceSchema, t as Category, tt as DocumentArchive, u as getCategory, ut as Parser, v as TasksV1Schema, vt as Source, w as GraphEdge, x as collectionOf, xt as WaybackTimestampSchema, y as Collection, yt as SourceSchema, z as Manifest } from "./categories-DUG7URRd.js";
+import { $ as CrosswalkReference, A as Catalogue, B as ManifestSchema, C as JsonScalarSchema, Ct as waybackUrl, D as GraphNodeSchema, E as GraphNode, F as NamespaceNode, G as ArchiveMember, H as parseManifest, I as createCatalogue, J as Citation, K as ArchiveMemberSchema, L as Lineage, M as CatalogueIndexSchema, N as Dataset, O as GraphV1, P as DatasetQuery, Q as ColumnNameSchema, R as LineageSchema, S as JsonScalar, St as parseEntry, T as GraphEdgeSchema, U as AliasSchema, V as SemVerSchema, W as Archive, X as CollectionArchive, Y as CitationSchema, Z as CollectionArchiveSchema, _ as TasksV1, _t as SnapshotSchema, a as CategoryTargets, at as IdSchema, b as Instance, bt as SubjectSchema, c as countTarget, ct as Namespace, d as getCollectionTarget, dt as ParserSchema, et as CrosswalkReferenceSchema, f as getTarget, ft as RESERVED_META_KEYS, g as TaskSchema, gt as Snapshot, h as Task, ht as RelativePathSchema, i as CategoryTarget, it as HttpUrlSchema, j as CatalogueIndex, k as GraphV1Schema, l as countedKeys, lt as NamespaceSchema, m as listCategories, mt as RecipeSchema, n as CategoryId, nt as Entry, o as CollectionTarget, ot as Licence, p as kindOf, pt as Recipe, q as ArchiveSchema, r as CategoryIdSchema, rt as EntrySchema, s as CountedKey, st as LicenceSchema, t as Category, tt as DocumentArchive, u as getCategory, ut as Parser, v as TasksV1Schema, vt as Source, w as GraphEdge, x as collectionOf, xt as WaybackTimestampSchema, y as Collection, yt as SourceSchema, z as Manifest } from "./categories-D9r42M9E.js";
 import { Crosswalk } from "crossmap";
 //#region src/errors.d.ts
 /** The root of this package's error taxonomy: every error keepset throws is a `KeepsetError`, so callers can catch the family with one check. */

package/dist/index.js

@@ -1,4 +1,4 @@
-import { $ as ArchiveError, A as WaybackTimestampSchema, B as countedKeys, C as ParserSchema, D as SnapshotSchema, E as RelativePathSchema, F as groupsOf, G as listCategories, H as getCollectionTarget, I as namesOf, J as collectionOf, K as TaskSchema, M as toIssues, N as waybackUrl, O as SourceSchema, P as NAME_SEPARATOR, Q as JsonScalarSchema, R as CategoryIdSchema, S as NamespaceSchema, T as RecipeSchema, U as getTarget, V as getCategory, W as kindOf, X as GraphNodeSchema, Y as GraphEdgeSchema, Z as GraphV1Schema, _ as CrosswalkReferenceSchema, a as CatalogueIndexSchema, at as RecipeError, b as IdSchema, c as ManifestSchema, d as AliasSchema, et as CatalogueSyntaxError, f as ArchiveMemberSchema, g as ColumnNameSchema, h as CollectionArchiveSchema, i as listNamespaces, it as NativeParseError, j as parseEntry, k as SubjectSchema, l as SemVerSchema, m as CitationSchema, n as getManifest, nt as DatasetNotFoundError, o as createCatalogue, ot as UnknownCategoryError, p as ArchiveSchema, q as TasksV1Schema, r as listDatasets, rt as KeepsetError, s as LineageSchema, t as getDataset, tt as DatasetAmbiguousError, u as parseManifest, v as EntrySchema, w as RESERVED_META_KEYS, x as LicenceSchema, y as HttpUrlSchema, z as countTarget } from "./bundled-CPSe9InV.js";
+import { $ as ArchiveError, A as WaybackTimestampSchema, B as countedKeys, C as ParserSchema, D as SnapshotSchema, E as RelativePathSchema, F as groupsOf, G as listCategories, H as getCollectionTarget, I as namesOf, J as collectionOf, K as TaskSchema, M as toIssues, N as waybackUrl, O as SourceSchema, P as NAME_SEPARATOR, Q as JsonScalarSchema, R as CategoryIdSchema, S as NamespaceSchema, T as RecipeSchema, U as getTarget, V as getCategory, W as kindOf, X as GraphNodeSchema, Y as GraphEdgeSchema, Z as GraphV1Schema, _ as CrosswalkReferenceSchema, a as CatalogueIndexSchema, at as RecipeError, b as IdSchema, c as ManifestSchema, d as AliasSchema, et as CatalogueSyntaxError, f as ArchiveMemberSchema, g as ColumnNameSchema, h as CollectionArchiveSchema, i as listNamespaces, it as NativeParseError, j as parseEntry, k as SubjectSchema, l as SemVerSchema, m as CitationSchema, n as getManifest, nt as DatasetNotFoundError, o as createCatalogue, ot as UnknownCategoryError, p as ArchiveSchema, q as TasksV1Schema, r as listDatasets, rt as KeepsetError, s as LineageSchema, t as getDataset, tt as DatasetAmbiguousError, u as parseManifest, v as EntrySchema, w as RESERVED_META_KEYS, x as LicenceSchema, y as HttpUrlSchema, z as countTarget } from "./bundled-BrTVG8j1.js";
 import { validateCrosswalk } from "crossmap";
 //#region src/serialise.ts
 /**

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

@@ -1,4 +1,4 @@
-import { N as Dataset, gt as Snapshot, i as CategoryTarget, nt as Entry, o as CollectionTarget, vt as Source } from "../categories-DUG7URRd.js";
+import { N as Dataset, gt as Snapshot, i as CategoryTarget, nt as Entry, o as CollectionTarget, vt as Source } from "../categories-D9r42M9E.js";
 //#region src/node/fetch-dataset.d.ts
 /** The network port a recipe downloads through: `downloadRaw` by default, which returns the bytes exactly as served, or a stand-in under test. */
 export type FetchPort = (url: string, init: {