keepset 0.38.0 → 0.39.0

package/dist/{categories-gZh8cn-G.d.ts → categories-DijttH_M.d.ts}

@@ -114,7 +114,7 @@ declare const PartsArchiveSchema: z.ZodObject<{
   }, z.core.$strict>>;
 }, z.core.$strict>;
 type PartsArchive = z.infer<typeof PartsArchiveSchema>;
-/** 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, 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. */
+/** 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. */
 declare const ArchiveSchema: z.ZodUnion<readonly [z.ZodObject<{
   kind: z.ZodLiteral<"none">;
 }, z.core.$strict>, z.ZodObject<{
@@ -194,6 +194,23 @@ declare const ArchiveSchema: z.ZodUnion<readonly [z.ZodObject<{
       pattern: z.ZodString;
     }, z.core.$strict>]>;
   }, z.core.$strict>>;
+}, z.core.$strict>, z.ZodObject<{
+  kind: z.ZodEnum<{
+    zip: "zip";
+    tar: "tar";
+    "tar.gz": "tar.gz";
+    "tar.bz2": "tar.bz2";
+  }>;
+  files: 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.$strict>]>;
+  inner: z.ZodOptional<z.ZodObject<{
+    kind: z.ZodLiteral<"gzip">;
+  }, z.core.$strict>>;
 }, z.core.$strict>, z.ZodObject<{
   kind: z.ZodEnum<{
     xlsx: "xlsx";
@@ -215,7 +232,9 @@ type Archive = z.infer<typeof ArchiveSchema>;
 /** An archive that gives the one file a document is read from. */
 type DocumentArchive = Exclude<Archive, {
   readonly members: ArchiveMember;
-} | PartsArchive>;
+} | PartsArchive | {
+  readonly files: ArchiveMember;
+}>;
 /** An archive that gives every file a collection is read from. */
 type CollectionArchive = z.infer<typeof CollectionArchiveSchema>;
 /** A column of a table as the table parser names it: the header with every run of characters outside letters, digits and underscore replaced by one underscore, so it is a valid segment of a crossmap path. */
@@ -244,6 +263,10 @@ declare const ParserSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
   }, z.core.$strict>>;
   multiplicityColumn: z.ZodOptional<z.ZodInt>;
   mirrored: z.ZodOptional<z.ZodLiteral<true>>;
+  where: z.ZodOptional<z.ZodArray<z.ZodObject<{
+    column: z.ZodInt;
+    equals: z.ZodString;
+  }, z.core.$strict>>>;
 }, z.core.$strict>, z.ZodObject<{
   format: z.ZodLiteral<"matrix-market">;
   encoding: z.ZodEnum<{
@@ -336,6 +359,9 @@ declare const ParserSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
 }, z.core.$strict>, z.ZodObject<{
   format: z.ZodLiteral<"witvliet-synapses">;
   encoding: z.ZodLiteral<"utf-8">;
+}, z.core.$strict>, z.ZodObject<{
+  format: z.ZodLiteral<"ogb">;
+  encoding: z.ZodLiteral<"utf-8">;
 }, z.core.$strict>, z.ZodObject<{
   format: z.ZodLiteral<"customer-points">;
   encoding: z.ZodEnum<{
@@ -501,6 +527,23 @@ declare const RecipeSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
         pattern: z.ZodString;
       }, z.core.$strict>]>;
     }, z.core.$strict>>;
+  }, z.core.$strict>, z.ZodObject<{
+    kind: z.ZodEnum<{
+      zip: "zip";
+      tar: "tar";
+      "tar.gz": "tar.gz";
+      "tar.bz2": "tar.bz2";
+    }>;
+    files: 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.$strict>]>;
+    inner: z.ZodOptional<z.ZodObject<{
+      kind: z.ZodLiteral<"gzip">;
+    }, z.core.$strict>>;
   }, z.core.$strict>, z.ZodObject<{
     kind: z.ZodEnum<{
       xlsx: "xlsx";
@@ -541,6 +584,10 @@ declare const RecipeSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
     }, z.core.$strict>>;
     multiplicityColumn: z.ZodOptional<z.ZodInt>;
     mirrored: z.ZodOptional<z.ZodLiteral<true>>;
+    where: z.ZodOptional<z.ZodArray<z.ZodObject<{
+      column: z.ZodInt;
+      equals: z.ZodString;
+    }, z.core.$strict>>>;
   }, z.core.$strict>, z.ZodObject<{
     format: z.ZodLiteral<"matrix-market">;
     encoding: z.ZodEnum<{
@@ -633,6 +680,9 @@ declare const RecipeSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
   }, z.core.$strict>, z.ZodObject<{
     format: z.ZodLiteral<"witvliet-synapses">;
     encoding: z.ZodLiteral<"utf-8">;
+  }, z.core.$strict>, z.ZodObject<{
+    format: z.ZodLiteral<"ogb">;
+    encoding: z.ZodLiteral<"utf-8">;
   }, z.core.$strict>, z.ZodObject<{
     format: z.ZodLiteral<"customer-points">;
     encoding: z.ZodEnum<{
@@ -854,6 +904,23 @@ declare const EntrySchema: z.ZodObject<{
           pattern: z.ZodString;
         }, z.core.$strict>]>;
       }, z.core.$strict>>;
+    }, z.core.$strict>, z.ZodObject<{
+      kind: z.ZodEnum<{
+        zip: "zip";
+        tar: "tar";
+        "tar.gz": "tar.gz";
+        "tar.bz2": "tar.bz2";
+      }>;
+      files: 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.$strict>]>;
+      inner: z.ZodOptional<z.ZodObject<{
+        kind: z.ZodLiteral<"gzip">;
+      }, z.core.$strict>>;
     }, z.core.$strict>, z.ZodObject<{
       kind: z.ZodEnum<{
         xlsx: "xlsx";
@@ -894,6 +961,10 @@ declare const EntrySchema: z.ZodObject<{
       }, z.core.$strict>>;
       multiplicityColumn: z.ZodOptional<z.ZodInt>;
       mirrored: z.ZodOptional<z.ZodLiteral<true>>;
+      where: z.ZodOptional<z.ZodArray<z.ZodObject<{
+        column: z.ZodInt;
+        equals: z.ZodString;
+      }, z.core.$strict>>>;
     }, z.core.$strict>, z.ZodObject<{
       format: z.ZodLiteral<"matrix-market">;
       encoding: z.ZodEnum<{
@@ -986,6 +1057,9 @@ declare const EntrySchema: z.ZodObject<{
     }, z.core.$strict>, z.ZodObject<{
       format: z.ZodLiteral<"witvliet-synapses">;
       encoding: z.ZodLiteral<"utf-8">;
+    }, z.core.$strict>, z.ZodObject<{
+      format: z.ZodLiteral<"ogb">;
+      encoding: z.ZodLiteral<"utf-8">;
     }, z.core.$strict>, z.ZodObject<{
       format: z.ZodLiteral<"customer-points">;
       encoding: z.ZodEnum<{
@@ -1112,6 +1186,18 @@ declare const EntrySchema: z.ZodObject<{
           kind: "xlsx";
           sheets?: string | undefined;
         } | undefined;
+      } | {
+        kind: "zip" | "tar" | "tar.gz" | "tar.bz2";
+        files: {
+          path: string;
+        } | {
+          extensions: string[];
+        } | {
+          pattern: string;
+        };
+        inner?: {
+          kind: "gzip";
+        } | undefined;
       } | {
         kind: "xlsx" | "xls" | "ods";
         sheet: string;
@@ -1181,6 +1267,10 @@ declare const EntrySchema: z.ZodObject<{
         } | undefined;
         multiplicityColumn?: number | undefined;
         mirrored?: true | undefined;
+        where?: {
+          column: number;
+          equals: string;
+        }[] | undefined;
       } | {
         format: "hgb";
         encoding: "utf-8";
@@ -1256,6 +1346,9 @@ declare const EntrySchema: z.ZodObject<{
       } | {
         format: "witvliet-synapses";
         encoding: "utf-8";
+      } | {
+        format: "ogb";
+        encoding: "utf-8";
       } | {
         format: "customer-points";
         encoding: "utf-8" | "latin1";
@@ -1538,6 +1631,23 @@ declare const CatalogueIndexSchema: z.ZodObject<{
             pattern: z.ZodString;
           }, z.core.$strict>]>;
         }, z.core.$strict>>;
+      }, z.core.$strict>, z.ZodObject<{
+        kind: z.ZodEnum<{
+          zip: "zip";
+          tar: "tar";
+          "tar.gz": "tar.gz";
+          "tar.bz2": "tar.bz2";
+        }>;
+        files: 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.$strict>]>;
+        inner: z.ZodOptional<z.ZodObject<{
+          kind: z.ZodLiteral<"gzip">;
+        }, z.core.$strict>>;
       }, z.core.$strict>, z.ZodObject<{
         kind: z.ZodEnum<{
           xlsx: "xlsx";
@@ -1578,6 +1688,10 @@ declare const CatalogueIndexSchema: z.ZodObject<{
         }, z.core.$strict>>;
         multiplicityColumn: z.ZodOptional<z.ZodInt>;
         mirrored: z.ZodOptional<z.ZodLiteral<true>>;
+        where: z.ZodOptional<z.ZodArray<z.ZodObject<{
+          column: z.ZodInt;
+          equals: z.ZodString;
+        }, z.core.$strict>>>;
       }, z.core.$strict>, z.ZodObject<{
         format: z.ZodLiteral<"matrix-market">;
         encoding: z.ZodEnum<{
@@ -1670,6 +1784,9 @@ declare const CatalogueIndexSchema: z.ZodObject<{
       }, z.core.$strict>, z.ZodObject<{
         format: z.ZodLiteral<"witvliet-synapses">;
         encoding: z.ZodLiteral<"utf-8">;
+      }, z.core.$strict>, z.ZodObject<{
+        format: z.ZodLiteral<"ogb">;
+        encoding: z.ZodLiteral<"utf-8">;
       }, z.core.$strict>, z.ZodObject<{
         format: z.ZodLiteral<"customer-points">;
         encoding: z.ZodEnum<{
@@ -1796,6 +1913,18 @@ declare const CatalogueIndexSchema: z.ZodObject<{
             kind: "xlsx";
             sheets?: string | undefined;
           } | undefined;
+        } | {
+          kind: "zip" | "tar" | "tar.gz" | "tar.bz2";
+          files: {
+            path: string;
+          } | {
+            extensions: string[];
+          } | {
+            pattern: string;
+          };
+          inner?: {
+            kind: "gzip";
+          } | undefined;
         } | {
           kind: "xlsx" | "xls" | "ods";
           sheet: string;
@@ -1865,6 +1994,10 @@ declare const CatalogueIndexSchema: z.ZodObject<{
           } | undefined;
           multiplicityColumn?: number | undefined;
           mirrored?: true | undefined;
+          where?: {
+            column: number;
+            equals: string;
+          }[] | undefined;
         } | {
           format: "hgb";
           encoding: "utf-8";
@@ -1940,6 +2073,9 @@ declare const CatalogueIndexSchema: z.ZodObject<{
         } | {
           format: "witvliet-synapses";
           encoding: "utf-8";
+        } | {
+          format: "ogb";
+          encoding: "utf-8";
         } | {
           format: "customer-points";
           encoding: "utf-8" | "latin1";
@@ -2055,6 +2191,18 @@ declare const CatalogueIndexSchema: z.ZodObject<{
             kind: "xlsx";
             sheets?: string | undefined;
           } | undefined;
+        } | {
+          kind: "zip" | "tar" | "tar.gz" | "tar.bz2";
+          files: {
+            path: string;
+          } | {
+            extensions: string[];
+          } | {
+            pattern: string;
+          };
+          inner?: {
+            kind: "gzip";
+          } | undefined;
         } | {
           kind: "xlsx" | "xls" | "ods";
           sheet: string;
@@ -2124,6 +2272,10 @@ declare const CatalogueIndexSchema: z.ZodObject<{
           } | undefined;
           multiplicityColumn?: number | undefined;
           mirrored?: true | undefined;
+          where?: {
+            column: number;
+            equals: string;
+          }[] | undefined;
         } | {
           format: "hgb";
           encoding: "utf-8";
@@ -2199,6 +2351,9 @@ declare const CatalogueIndexSchema: z.ZodObject<{
         } | {
           format: "witvliet-synapses";
           encoding: "utf-8";
+        } | {
+          format: "ogb";
+          encoding: "utf-8";
         } | {
           format: "customer-points";
           encoding: "utf-8" | "latin1";

package/dist/index.d.ts

@@ -1,4 +1,4 @@
-import { $ as CrosswalkReference, A as Catalogue, B as ManifestSchema, C as JsonScalarSchema, Ct as parseEntry, 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 WaybackTimestampSchema, 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 Snapshot, a as CategoryTargets, at as IdSchema, b as Instance, bt as SourceSchema, c as countTarget, ct as Namespace, d as getCollectionTarget, dt as ParserSchema, et as CrosswalkReferenceSchema, f as getTarget, ft as PartsArchive, g as TaskSchema, gt as RelativePathSchema, h as Task, ht as RecipeSchema, i as CategoryTarget, it as HttpUrlSchema, j as CatalogueIndex, k as GraphV1Schema, l as countedKeys, lt as NamespaceSchema, m as listCategories, mt as Recipe, n as CategoryId, nt as Entry, o as CollectionTarget, ot as Licence, p as kindOf, pt as RESERVED_META_KEYS, 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 SnapshotSchema, w as GraphEdge, wt as waybackUrl, x as collectionOf, xt as SubjectSchema, y as Collection, yt as Source, z as Manifest } from "./categories-gZh8cn-G.js";
+import { $ as CrosswalkReference, A as Catalogue, B as ManifestSchema, C as JsonScalarSchema, Ct as parseEntry, 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 WaybackTimestampSchema, 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 Snapshot, a as CategoryTargets, at as IdSchema, b as Instance, bt as SourceSchema, c as countTarget, ct as Namespace, d as getCollectionTarget, dt as ParserSchema, et as CrosswalkReferenceSchema, f as getTarget, ft as PartsArchive, g as TaskSchema, gt as RelativePathSchema, h as Task, ht as RecipeSchema, i as CategoryTarget, it as HttpUrlSchema, j as CatalogueIndex, k as GraphV1Schema, l as countedKeys, lt as NamespaceSchema, m as listCategories, mt as Recipe, n as CategoryId, nt as Entry, o as CollectionTarget, ot as Licence, p as kindOf, pt as RESERVED_META_KEYS, 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 SnapshotSchema, w as GraphEdge, wt as waybackUrl, x as collectionOf, xt as SubjectSchema, y as Collection, yt as Source, z as Manifest } from "./categories-DijttH_M.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-U2l4WT5T.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-6dYCPVD-.js";
 import { validateCrosswalk } from "crossmap";
 //#region src/serialise.ts
 /**

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

@@ -1,4 +1,4 @@
-import { N as Dataset, _t as Snapshot, i as CategoryTarget, nt as Entry, o as CollectionTarget, yt as Source } from "../categories-gZh8cn-G.js";
+import { N as Dataset, _t as Snapshot, i as CategoryTarget, nt as Entry, o as CollectionTarget, yt as Source } from "../categories-DijttH_M.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: {
@@ -26,7 +26,7 @@ export interface Provenance {
   readonly byteLength: number;
   /** The archive member a document was read from. */
   readonly member?: string;
-  /** The archive members a collection, or a document read from named parts, was read from, in the order they were read. */
+  /** The archive members a collection, or a document read from several files, was read from, in the order they were read. */
   readonly members?: readonly string[];
 }
 /** A fetched dataset: the resolved category target (one document, or for a recipe that selects archive members a collection of them), the provenance of the bytes it came from, and any warnings, such as a count that differs from the one the entry records. */