keepset 0.33.0 → 0.34.0

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

@@ -80,6 +80,7 @@ declare const CollectionArchiveSchema: z.ZodObject<{
     zip: "zip";
     tar: "tar";
     "tar.gz": "tar.gz";
+    "tar.bz2": "tar.bz2";
   }>;
   members: z.ZodUnion<readonly [z.ZodObject<{
     path: z.ZodString;
@@ -89,16 +90,19 @@ declare const CollectionArchiveSchema: z.ZodObject<{
     pattern: 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. 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. */
 declare const ArchiveSchema: z.ZodUnion<readonly [z.ZodObject<{
   kind: z.ZodLiteral<"none">;
 }, z.core.$strict>, z.ZodObject<{
   kind: z.ZodLiteral<"gzip">;
+}, z.core.$strict>, z.ZodObject<{
+  kind: z.ZodLiteral<"bzip2">;
 }, z.core.$strict>, z.ZodObject<{
   kind: z.ZodEnum<{
     zip: "zip";
     tar: "tar";
     "tar.gz": "tar.gz";
+    "tar.bz2": "tar.bz2";
   }>;
   member: z.ZodUnion<readonly [z.ZodObject<{
     path: z.ZodString;
@@ -114,6 +118,7 @@ declare const ArchiveSchema: z.ZodUnion<readonly [z.ZodObject<{
       zip: "zip";
       tar: "tar";
       "tar.gz": "tar.gz";
+      "tar.bz2": "tar.bz2";
     }>;
     member: z.ZodUnion<readonly [z.ZodObject<{
       path: z.ZodString;
@@ -128,6 +133,7 @@ declare const ArchiveSchema: z.ZodUnion<readonly [z.ZodObject<{
     zip: "zip";
     tar: "tar";
     "tar.gz": "tar.gz";
+    "tar.bz2": "tar.bz2";
   }>;
   members: z.ZodUnion<readonly [z.ZodObject<{
     path: z.ZodString;
@@ -173,6 +179,25 @@ declare const ParserSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
     "utf-8": "utf-8";
     latin1: "latin1";
   }>;
+}, z.core.$strict>, z.ZodObject<{
+  format: z.ZodLiteral<"user-item-ratings">;
+  encoding: z.ZodLiteral<"utf-8">;
+  delimiter: z.ZodEnum<{
+    tab: "tab";
+    comma: "comma";
+    "double-colon": "double-colon";
+  }>;
+  skipLines: z.ZodInt;
+  itemType: z.ZodEnum<{
+    movie: "movie";
+    product: "product";
+  }>;
+  maxRating: z.ZodNumber;
+}, z.core.$strict>, z.ZodObject<{
+  format: z.ZodLiteral<"konect">;
+  encoding: z.ZodLiteral<"utf-8">;
+  weighted: z.ZodBoolean;
+  timestamped: z.ZodBoolean;
 }, z.core.$strict>, z.ZodObject<{
   format: z.ZodLiteral<"gml">;
   encoding: z.ZodEnum<{
@@ -286,11 +311,14 @@ declare const RecipeSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
     kind: z.ZodLiteral<"none">;
   }, z.core.$strict>, z.ZodObject<{
     kind: z.ZodLiteral<"gzip">;
+  }, z.core.$strict>, z.ZodObject<{
+    kind: z.ZodLiteral<"bzip2">;
   }, z.core.$strict>, z.ZodObject<{
     kind: z.ZodEnum<{
       zip: "zip";
       tar: "tar";
       "tar.gz": "tar.gz";
+      "tar.bz2": "tar.bz2";
     }>;
     member: z.ZodUnion<readonly [z.ZodObject<{
       path: z.ZodString;
@@ -306,6 +334,7 @@ declare const RecipeSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
         zip: "zip";
         tar: "tar";
         "tar.gz": "tar.gz";
+        "tar.bz2": "tar.bz2";
       }>;
       member: z.ZodUnion<readonly [z.ZodObject<{
         path: z.ZodString;
@@ -320,6 +349,7 @@ declare const RecipeSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
       zip: "zip";
       tar: "tar";
       "tar.gz": "tar.gz";
+      "tar.bz2": "tar.bz2";
     }>;
     members: z.ZodUnion<readonly [z.ZodObject<{
       path: z.ZodString;
@@ -355,6 +385,25 @@ declare const RecipeSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
       "utf-8": "utf-8";
       latin1: "latin1";
     }>;
+  }, z.core.$strict>, z.ZodObject<{
+    format: z.ZodLiteral<"user-item-ratings">;
+    encoding: z.ZodLiteral<"utf-8">;
+    delimiter: z.ZodEnum<{
+      tab: "tab";
+      comma: "comma";
+      "double-colon": "double-colon";
+    }>;
+    skipLines: z.ZodInt;
+    itemType: z.ZodEnum<{
+      movie: "movie";
+      product: "product";
+    }>;
+    maxRating: z.ZodNumber;
+  }, z.core.$strict>, z.ZodObject<{
+    format: z.ZodLiteral<"konect">;
+    encoding: z.ZodLiteral<"utf-8">;
+    weighted: z.ZodBoolean;
+    timestamped: z.ZodBoolean;
   }, z.core.$strict>, z.ZodObject<{
     format: z.ZodLiteral<"gml">;
     encoding: z.ZodEnum<{
@@ -523,11 +572,14 @@ declare const EntrySchema: z.ZodObject<{
       kind: z.ZodLiteral<"none">;
     }, z.core.$strict>, z.ZodObject<{
       kind: z.ZodLiteral<"gzip">;
+    }, z.core.$strict>, z.ZodObject<{
+      kind: z.ZodLiteral<"bzip2">;
     }, z.core.$strict>, z.ZodObject<{
       kind: z.ZodEnum<{
         zip: "zip";
         tar: "tar";
         "tar.gz": "tar.gz";
+        "tar.bz2": "tar.bz2";
       }>;
       member: z.ZodUnion<readonly [z.ZodObject<{
         path: z.ZodString;
@@ -543,6 +595,7 @@ declare const EntrySchema: z.ZodObject<{
           zip: "zip";
           tar: "tar";
           "tar.gz": "tar.gz";
+          "tar.bz2": "tar.bz2";
         }>;
         member: z.ZodUnion<readonly [z.ZodObject<{
           path: z.ZodString;
@@ -557,6 +610,7 @@ declare const EntrySchema: z.ZodObject<{
         zip: "zip";
         tar: "tar";
         "tar.gz": "tar.gz";
+        "tar.bz2": "tar.bz2";
       }>;
       members: z.ZodUnion<readonly [z.ZodObject<{
         path: z.ZodString;
@@ -592,6 +646,25 @@ declare const EntrySchema: z.ZodObject<{
         "utf-8": "utf-8";
         latin1: "latin1";
       }>;
+    }, z.core.$strict>, z.ZodObject<{
+      format: z.ZodLiteral<"user-item-ratings">;
+      encoding: z.ZodLiteral<"utf-8">;
+      delimiter: z.ZodEnum<{
+        tab: "tab";
+        comma: "comma";
+        "double-colon": "double-colon";
+      }>;
+      skipLines: z.ZodInt;
+      itemType: z.ZodEnum<{
+        movie: "movie";
+        product: "product";
+      }>;
+      maxRating: z.ZodNumber;
+    }, z.core.$strict>, z.ZodObject<{
+      format: z.ZodLiteral<"konect">;
+      encoding: z.ZodLiteral<"utf-8">;
+      weighted: z.ZodBoolean;
+      timestamped: z.ZodBoolean;
     }, z.core.$strict>, z.ZodObject<{
       format: z.ZodLiteral<"gml">;
       encoding: z.ZodEnum<{
@@ -728,7 +801,7 @@ declare const EntrySchema: z.ZodObject<{
       status: "fetchable";
       source: number;
       archive: {
-        kind: "zip" | "tar" | "tar.gz";
+        kind: "zip" | "tar" | "tar.gz" | "tar.bz2";
         members: {
           path: string;
         } | {
@@ -741,7 +814,9 @@ declare const EntrySchema: z.ZodObject<{
       } | {
         kind: "gzip";
       } | {
-        kind: "zip" | "tar" | "tar.gz";
+        kind: "bzip2";
+      } | {
+        kind: "zip" | "tar" | "tar.gz" | "tar.bz2";
         member: {
           path: string;
         } | {
@@ -752,7 +827,7 @@ declare const EntrySchema: z.ZodObject<{
         inner?: {
           kind: "gzip";
         } | {
-          kind: "zip" | "tar" | "tar.gz";
+          kind: "zip" | "tar" | "tar.gz" | "tar.bz2";
           member: {
             path: string;
           } | {
@@ -798,6 +873,18 @@ declare const EntrySchema: z.ZodObject<{
       } | {
         format: "matrix-market";
         encoding: "utf-8" | "latin1";
+      } | {
+        format: "user-item-ratings";
+        encoding: "utf-8";
+        delimiter: "tab" | "comma" | "double-colon";
+        skipLines: number;
+        itemType: "movie" | "product";
+        maxRating: number;
+      } | {
+        format: "konect";
+        encoding: "utf-8";
+        weighted: boolean;
+        timestamped: boolean;
       } | {
         format: "gml";
         encoding: "utf-8" | "latin1";
@@ -1015,11 +1102,14 @@ declare const CatalogueIndexSchema: z.ZodObject<{
         kind: z.ZodLiteral<"none">;
       }, z.core.$strict>, z.ZodObject<{
         kind: z.ZodLiteral<"gzip">;
+      }, z.core.$strict>, z.ZodObject<{
+        kind: z.ZodLiteral<"bzip2">;
       }, z.core.$strict>, z.ZodObject<{
         kind: z.ZodEnum<{
           zip: "zip";
           tar: "tar";
           "tar.gz": "tar.gz";
+          "tar.bz2": "tar.bz2";
         }>;
         member: z.ZodUnion<readonly [z.ZodObject<{
           path: z.ZodString;
@@ -1035,6 +1125,7 @@ declare const CatalogueIndexSchema: z.ZodObject<{
             zip: "zip";
             tar: "tar";
             "tar.gz": "tar.gz";
+            "tar.bz2": "tar.bz2";
           }>;
           member: z.ZodUnion<readonly [z.ZodObject<{
             path: z.ZodString;
@@ -1049,6 +1140,7 @@ declare const CatalogueIndexSchema: z.ZodObject<{
           zip: "zip";
           tar: "tar";
           "tar.gz": "tar.gz";
+          "tar.bz2": "tar.bz2";
         }>;
         members: z.ZodUnion<readonly [z.ZodObject<{
           path: z.ZodString;
@@ -1084,6 +1176,25 @@ declare const CatalogueIndexSchema: z.ZodObject<{
           "utf-8": "utf-8";
           latin1: "latin1";
         }>;
+      }, z.core.$strict>, z.ZodObject<{
+        format: z.ZodLiteral<"user-item-ratings">;
+        encoding: z.ZodLiteral<"utf-8">;
+        delimiter: z.ZodEnum<{
+          tab: "tab";
+          comma: "comma";
+          "double-colon": "double-colon";
+        }>;
+        skipLines: z.ZodInt;
+        itemType: z.ZodEnum<{
+          movie: "movie";
+          product: "product";
+        }>;
+        maxRating: z.ZodNumber;
+      }, z.core.$strict>, z.ZodObject<{
+        format: z.ZodLiteral<"konect">;
+        encoding: z.ZodLiteral<"utf-8">;
+        weighted: z.ZodBoolean;
+        timestamped: z.ZodBoolean;
       }, z.core.$strict>, z.ZodObject<{
         format: z.ZodLiteral<"gml">;
         encoding: z.ZodEnum<{
@@ -1220,7 +1331,7 @@ declare const CatalogueIndexSchema: z.ZodObject<{
         status: "fetchable";
         source: number;
         archive: {
-          kind: "zip" | "tar" | "tar.gz";
+          kind: "zip" | "tar" | "tar.gz" | "tar.bz2";
           members: {
             path: string;
           } | {
@@ -1233,7 +1344,9 @@ declare const CatalogueIndexSchema: z.ZodObject<{
         } | {
           kind: "gzip";
         } | {
-          kind: "zip" | "tar" | "tar.gz";
+          kind: "bzip2";
+        } | {
+          kind: "zip" | "tar" | "tar.gz" | "tar.bz2";
           member: {
             path: string;
           } | {
@@ -1244,7 +1357,7 @@ declare const CatalogueIndexSchema: z.ZodObject<{
           inner?: {
             kind: "gzip";
           } | {
-            kind: "zip" | "tar" | "tar.gz";
+            kind: "zip" | "tar" | "tar.gz" | "tar.bz2";
             member: {
               path: string;
             } | {
@@ -1290,6 +1403,18 @@ declare const CatalogueIndexSchema: z.ZodObject<{
         } | {
           format: "matrix-market";
           encoding: "utf-8" | "latin1";
+        } | {
+          format: "user-item-ratings";
+          encoding: "utf-8";
+          delimiter: "tab" | "comma" | "double-colon";
+          skipLines: number;
+          itemType: "movie" | "product";
+          maxRating: number;
+        } | {
+          format: "konect";
+          encoding: "utf-8";
+          weighted: boolean;
+          timestamped: boolean;
         } | {
           format: "gml";
           encoding: "utf-8" | "latin1";
@@ -1403,7 +1528,7 @@ declare const CatalogueIndexSchema: z.ZodObject<{
         status: "fetchable";
         source: number;
         archive: {
-          kind: "zip" | "tar" | "tar.gz";
+          kind: "zip" | "tar" | "tar.gz" | "tar.bz2";
           members: {
             path: string;
           } | {
@@ -1416,7 +1541,9 @@ declare const CatalogueIndexSchema: z.ZodObject<{
         } | {
           kind: "gzip";
         } | {
-          kind: "zip" | "tar" | "tar.gz";
+          kind: "bzip2";
+        } | {
+          kind: "zip" | "tar" | "tar.gz" | "tar.bz2";
           member: {
             path: string;
           } | {
@@ -1427,7 +1554,7 @@ declare const CatalogueIndexSchema: z.ZodObject<{
           inner?: {
             kind: "gzip";
           } | {
-            kind: "zip" | "tar" | "tar.gz";
+            kind: "zip" | "tar" | "tar.gz" | "tar.bz2";
             member: {
               path: string;
             } | {
@@ -1473,6 +1600,18 @@ declare const CatalogueIndexSchema: z.ZodObject<{
         } | {
           format: "matrix-market";
           encoding: "utf-8" | "latin1";
+        } | {
+          format: "user-item-ratings";
+          encoding: "utf-8";
+          delimiter: "tab" | "comma" | "double-colon";
+          skipLines: number;
+          itemType: "movie" | "product";
+          maxRating: number;
+        } | {
+          format: "konect";
+          encoding: "utf-8";
+          weighted: boolean;
+          timestamped: boolean;
         } | {
           format: "gml";
           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 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-HwqAn-Lc.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-DUG7URRd.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-pT7q4sWm.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-CPSe9InV.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-HwqAn-Lc.js";
+import { N as Dataset, gt as Snapshot, i as CategoryTarget, nt as Entry, o as CollectionTarget, vt as Source } from "../categories-DUG7URRd.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: {