@graphty/graph-samples 0.0.1 → 0.1.1

package/dist/graph-samples.d.ts

@@ -0,0 +1 @@
+export * from "./src/index.js";

package/dist/graph-samples.js

@@ -0,0 +1,142 @@
+import { c as celegansNeuralMeta } from "./chunks/meta-DrgM1eS0.js";
+import { c as contiguousUsaMeta } from "./chunks/meta-MQPbBUUB.js";
+import { d as davisSouthernWomenMeta } from "./chunks/meta-BaFPvhc1.js";
+import { d as dolphinsMeta } from "./chunks/meta-mns0uFIW.js";
+import { f as florentineFamiliesMeta } from "./chunks/meta-B6toBzaa.js";
+import { f as footballMeta } from "./chunks/meta-IhoaDXAV.js";
+import { k as karateMeta } from "./chunks/meta-Qp4HNYAZ.js";
+import { k as knuthMilesMeta } from "./chunks/meta-BM_YIhlA.js";
+import { l as lesMiserablesMeta } from "./chunks/meta-CQRXyexG.js";
+import { o as openflightsMeta } from "./chunks/meta-BMmtUpPx.js";
+import { p as politicalBlogsMeta } from "./chunks/meta-C58v1Oy0.js";
+import { p as politicalBooksMeta } from "./chunks/meta-BXC7oi86.js";
+import { fromBytes } from "@graphty/graph-format";
+const HOSTED_DATASETS = [
+  {
+    name: "road-ny",
+    title: "New York City road network (DIMACS)",
+    description: "Road intersections of the New York City area and the road segments between them, from the US Census TIGER/Line files as prepared for the 9th DIMACS shortest-path challenge. Every road is two opposite arcs, weighted by its length in the challenge's integer distance units; each intersection carries its longitude and latitude.",
+    citation: "C. Demetrescu, A. V. Goldberg and D. S. Johnson (eds.), The Shortest Path Problem: Ninth DIMACS Implementation Challenge, DIMACS Series in Discrete Mathematics and Theoretical Computer Science 74, AMS (2009). Data: US Census Bureau TIGER/Line.",
+    source: "http://www.diag.uniroma1.it/challenge9/data/USA-road-d/USA-road-d.NY.gr.gz",
+    license: "Public domain: derived from the US Census Bureau TIGER/Line files, a work of the US federal government; the challenge page states no further terms.",
+    nodes: 264346,
+    edges: 733846,
+    directed: true,
+    weighted: true,
+    attributes: {
+      longitude: "f64: degrees east (negative: west)",
+      latitude: "f64: degrees north"
+    },
+    groundTruth: null,
+    showcases: [
+      "Dijkstra, bidirectional search and A* with a geographic heuristic",
+      "geographic layout of a quarter of a million nodes",
+      "minimum spanning trees and connectivity at scale"
+    ],
+    hosting: "remote",
+    bytes: 9424352,
+    sha256: "8c95611b0aa1e8aafe60eaac3aa716395f7fdf2a4d99b286b8b4b36ba58050f4"
+  },
+  {
+    name: "ogbn-arxiv",
+    title: "arXiv computer-science citations (ogbn-arxiv)",
+    description: "Citations among the computer-science arXiv papers indexed by the Microsoft Academic Graph, from the Open Graph Benchmark. An arc runs from the citing paper to the cited one. Each paper carries its publication year and its arXiv subject area, one of 40 (the ground truth); the benchmark's 128-dimensional text features are not included.",
+    citation: "W. Hu, M. Fey, M. Zitnik, Y. Dong, H. Ren, B. Liu, M. Catasta and J. Leskovec, Open Graph Benchmark: Datasets for Machine Learning on Graphs, NeurIPS 2020. arXiv:2005.00687; K. Wang, Z. Shen, C. Huang, C.-H. Wu, Y. Dong and A. Kanakia, Microsoft Academic Graph: When experts are not enough, Quantitative Science Studies 1(1), 396-413 (2020). doi:10.1162/qss_a_00021",
+    source: "http://snap.stanford.edu/ogb/data/nodeproppred/arxiv.zip",
+    license: "ODC-BY 1.0 (Open Data Commons Attribution License), as stated by the Open Graph Benchmark.",
+    nodes: 169343,
+    edges: 1166243,
+    directed: true,
+    weighted: false,
+    attributes: {
+      year: "u32: the publication year",
+      subject: 'dict: the arXiv subject area, e.g. "cs.LG" (ground truth)'
+    },
+    groundTruth: "subject",
+    showcases: [
+      "PageRank and citation counts at 170k nodes",
+      "community detection against 40 subject areas",
+      "near-DAG structure: strongly connected components, topological order by year"
+    ],
+    hosting: "remote",
+    bytes: 10637546,
+    sha256: "21c10fe0832a14ec628e7f221d70425b47dd879f9faf4e8a7650a9ade52ece9c"
+  },
+  {
+    name: "com-dblp",
+    title: "DBLP co-authorship (SNAP com-DBLP)",
+    description: "Co-authorship among computer scientists in the DBLP bibliography, as prepared by SNAP: two authors are joined when they published at least one paper together. Node ids are SNAP's author numbers. SNAP's ground-truth venue communities overlap, so they are not included as a column.",
+    citation: "J. Yang and J. Leskovec, Defining and evaluating network communities based on ground-truth, IEEE ICDM 2012, 745-754. doi:10.1109/ICDM.2012.138; dblp computer science bibliography, https://dblp.org",
+    source: "https://snap.stanford.edu/data/bigdata/communities/com-dblp.ungraph.txt.gz",
+    license: "unclear: SNAP states no license for its files; the underlying dblp data is CC0 1.0 (https://dblp.org/db/about/copyright.html).",
+    nodes: 317080,
+    edges: 1049866,
+    directed: false,
+    weighted: false,
+    attributes: {},
+    groundTruth: null,
+    showcases: [
+      "community detection (Louvain, Leiden, label propagation) at 300k nodes",
+      "k-core decomposition and clustering coefficients",
+      "degree distributions of a real collaboration network"
+    ],
+    hosting: "remote",
+    bytes: 15625518,
+    sha256: "c253f5f591d4e8076d05951ae702e4327f32e5db61381365ec2c86d237a0cdb0"
+  }
+];
+const DATASETS = [
+  karateMeta,
+  florentineFamiliesMeta,
+  davisSouthernWomenMeta,
+  lesMiserablesMeta,
+  footballMeta,
+  politicalBooksMeta,
+  dolphinsMeta,
+  contiguousUsaMeta,
+  knuthMilesMeta,
+  celegansNeuralMeta,
+  politicalBlogsMeta,
+  openflightsMeta,
+  ...HOSTED_DATASETS
+];
+const DEFAULT_DATASET_BASE_URL = "https://graphty.app/data/graph-samples/v1/";
+async function fetchDataset(name, options = {}) {
+  if (!/^[a-z0-9][a-z0-9-]*$/.test(name)) {
+    throw new RangeError(`not a dataset name: ${JSON.stringify(name)}`);
+  }
+  const base = options.baseUrl ?? DEFAULT_DATASET_BASE_URL;
+  const url = new URL(`${name}.gsnp.gz`, base.endsWith("/") ? base : `${base}/`);
+  const response = await (options.fetch ?? fetch)(url, { signal: options.signal ?? null });
+  if (!response.ok || response.body === null) {
+    throw new Error(`fetching ${url.href} failed: HTTP ${response.status}`);
+  }
+  const unzipped = response.body.pipeThrough(new DecompressionStream("gzip"));
+  return fromBytes(new Uint8Array(await new Response(unzipped).arrayBuffer()));
+}
+function toElementData(graph) {
+  const { ids, src, dst, weights } = graph;
+  const columns = Object.entries(graph.nodeColumns ?? {}).map(
+    ([name, column]) => [name, ArrayBuffer.isView(column) ? column : column.data]
+  );
+  const idOf = (i) => ids === void 0 ? i : ids[i];
+  const nodes = Array.from({ length: graph.nodeCount }, (_, i) => {
+    const record = { id: idOf(i) };
+    for (const [name, data] of columns) {
+      record[name] = data[i];
+    }
+    return record;
+  });
+  const edges = Array.from(
+    src,
+    (u, e) => weights === void 0 ? { source: idOf(u), target: idOf(dst[e]) } : { source: idOf(u), target: idOf(dst[e]), weight: weights[e] }
+  );
+  return { nodes, edges };
+}
+export {
+  DATASETS,
+  DEFAULT_DATASET_BASE_URL,
+  fetchDataset,
+  toElementData
+};
+//# sourceMappingURL=graph-samples.js.map

package/dist/graph-samples.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"graph-samples.js","sources":["../src/datasets/hosted.ts","../src/datasets/catalog.ts","../src/datasets/remote.ts","../src/element.ts"],"sourcesContent":["// THIS FILE IS AUTO GENERATED: DO NOT EDIT THIS FILE. INSTEAD EDIT graph-samples/scripts/build-hosted.mjs\n\nimport { type DatasetMeta } from \"./build.js\";\n\n/**\n * The metadata of every hosted dataset: too large to bundle, loaded with `fetchDataset(name)` from\n * https://graphty.app/data/graph-samples/v1/. `sha256` and `bytes` describe the published .gsnp.gz file.\n */\nexport const HOSTED_DATASETS: readonly DatasetMeta[] = [\n    {\n        name: \"road-ny\",\n        title: \"New York City road network (DIMACS)\",\n        description:\n            \"Road intersections of the New York City area and the road segments between them, from the US Census TIGER/Line files as prepared for the 9th DIMACS shortest-path challenge. Every road is two opposite arcs, weighted by its length in the challenge's integer distance units; each intersection carries its longitude and latitude.\",\n        citation:\n            \"C. Demetrescu, A. V. Goldberg and D. S. Johnson (eds.), The Shortest Path Problem: Ninth DIMACS Implementation Challenge, DIMACS Series in Discrete Mathematics and Theoretical Computer Science 74, AMS (2009). Data: US Census Bureau TIGER/Line.\",\n        source: \"http://www.diag.uniroma1.it/challenge9/data/USA-road-d/USA-road-d.NY.gr.gz\",\n        license:\n            \"Public domain: derived from the US Census Bureau TIGER/Line files, a work of the US federal government; the challenge page states no further terms.\",\n        nodes: 264346,\n        edges: 733846,\n        directed: true,\n        weighted: true,\n        attributes: {\n            longitude: \"f64: degrees east (negative: west)\",\n            latitude: \"f64: degrees north\",\n        },\n        groundTruth: null,\n        showcases: [\n            \"Dijkstra, bidirectional search and A* with a geographic heuristic\",\n            \"geographic layout of a quarter of a million nodes\",\n            \"minimum spanning trees and connectivity at scale\",\n        ],\n        hosting: \"remote\",\n        bytes: 9424352,\n        sha256: \"8c95611b0aa1e8aafe60eaac3aa716395f7fdf2a4d99b286b8b4b36ba58050f4\",\n    },\n    {\n        name: \"ogbn-arxiv\",\n        title: \"arXiv computer-science citations (ogbn-arxiv)\",\n        description:\n            \"Citations among the computer-science arXiv papers indexed by the Microsoft Academic Graph, from the Open Graph Benchmark. An arc runs from the citing paper to the cited one. Each paper carries its publication year and its arXiv subject area, one of 40 (the ground truth); the benchmark's 128-dimensional text features are not included.\",\n        citation:\n            \"W. Hu, M. Fey, M. Zitnik, Y. Dong, H. Ren, B. Liu, M. Catasta and J. Leskovec, Open Graph Benchmark: Datasets for Machine Learning on Graphs, NeurIPS 2020. arXiv:2005.00687; K. Wang, Z. Shen, C. Huang, C.-H. Wu, Y. Dong and A. Kanakia, Microsoft Academic Graph: When experts are not enough, Quantitative Science Studies 1(1), 396-413 (2020). doi:10.1162/qss_a_00021\",\n        source: \"http://snap.stanford.edu/ogb/data/nodeproppred/arxiv.zip\",\n        license: \"ODC-BY 1.0 (Open Data Commons Attribution License), as stated by the Open Graph Benchmark.\",\n        nodes: 169343,\n        edges: 1166243,\n        directed: true,\n        weighted: false,\n        attributes: {\n            year: \"u32: the publication year\",\n            subject: 'dict: the arXiv subject area, e.g. \"cs.LG\" (ground truth)',\n        },\n        groundTruth: \"subject\",\n        showcases: [\n            \"PageRank and citation counts at 170k nodes\",\n            \"community detection against 40 subject areas\",\n            \"near-DAG structure: strongly connected components, topological order by year\",\n        ],\n        hosting: \"remote\",\n        bytes: 10637546,\n        sha256: \"21c10fe0832a14ec628e7f221d70425b47dd879f9faf4e8a7650a9ade52ece9c\",\n    },\n    {\n        name: \"com-dblp\",\n        title: \"DBLP co-authorship (SNAP com-DBLP)\",\n        description:\n            \"Co-authorship among computer scientists in the DBLP bibliography, as prepared by SNAP: two authors are joined when they published at least one paper together. Node ids are SNAP's author numbers. SNAP's ground-truth venue communities overlap, so they are not included as a column.\",\n        citation:\n            \"J. Yang and J. Leskovec, Defining and evaluating network communities based on ground-truth, IEEE ICDM 2012, 745-754. doi:10.1109/ICDM.2012.138; dblp computer science bibliography, https://dblp.org\",\n        source: \"https://snap.stanford.edu/data/bigdata/communities/com-dblp.ungraph.txt.gz\",\n        license:\n            \"unclear: SNAP states no license for its files; the underlying dblp data is CC0 1.0 (https://dblp.org/db/about/copyright.html).\",\n        nodes: 317080,\n        edges: 1049866,\n        directed: false,\n        weighted: false,\n        attributes: {},\n        groundTruth: null,\n        showcases: [\n            \"community detection (Louvain, Leiden, label propagation) at 300k nodes\",\n            \"k-core decomposition and clustering coefficients\",\n            \"degree distributions of a real collaboration network\",\n        ],\n        hosting: \"remote\",\n        bytes: 15625518,\n        sha256: \"c253f5f591d4e8076d05951ae702e4327f32e5db61381365ec2c86d237a0cdb0\",\n    },\n];\n","import { type DatasetMeta } from \"./build.js\";\nimport { celegansNeuralMeta } from \"./celegans-neural/meta.js\";\nimport { contiguousUsaMeta } from \"./contiguous-usa/meta.js\";\nimport { davisSouthernWomenMeta } from \"./davis-southern-women/meta.js\";\nimport { dolphinsMeta } from \"./dolphins/meta.js\";\nimport { florentineFamiliesMeta } from \"./florentine-families/meta.js\";\nimport { footballMeta } from \"./football/meta.js\";\nimport { HOSTED_DATASETS } from \"./hosted.js\";\nimport { karateMeta } from \"./karate/meta.js\";\nimport { knuthMilesMeta } from \"./knuth-miles/meta.js\";\nimport { lesMiserablesMeta } from \"./les-miserables/meta.js\";\nimport { openflightsMeta } from \"./openflights/meta.js\";\nimport { politicalBlogsMeta } from \"./political-blogs/meta.js\";\nimport { politicalBooksMeta } from \"./political-books/meta.js\";\n\n/**\n * The metadata of every dataset (no graph data). A bundled dataset's edges load only from its own\n * subpath, `@graphty/graph-samples/datasets/<name>`; a dataset with `hosting: \"remote\"` loads with\n * `fetchDataset(name)`.\n */\nexport const DATASETS: readonly DatasetMeta[] = [\n    karateMeta,\n    florentineFamiliesMeta,\n    davisSouthernWomenMeta,\n    lesMiserablesMeta,\n    footballMeta,\n    politicalBooksMeta,\n    dolphinsMeta,\n    contiguousUsaMeta,\n    knuthMilesMeta,\n    celegansNeuralMeta,\n    politicalBlogsMeta,\n    openflightsMeta,\n    ...HOSTED_DATASETS,\n];\n","/**\n * Datasets too large to bundle (over about 5,000 nodes) are hosted on graphty.app as\n * graph-format wire bytes and fetched at runtime.\n */\n\nimport { fromBytes, type GraphSnapshot } from \"@graphty/graph-format\";\n\n/**\n * Where hosted datasets live: `<base><name>.gsnp.gz`, a gzipped graph-format wire container.\n * The `v1` segment is the hosting layout's version, independent of the package version.\n */\nexport const DEFAULT_DATASET_BASE_URL = \"https://graphty.app/data/graph-samples/v1/\";\n\n/** Options of {@link fetchDataset}. */\nexport interface FetchDatasetOptions {\n    /** Serve the files from elsewhere (self-hosting, a mirror, a test server). */\n    baseUrl?: string | undefined;\n    /** The fetch implementation; the global `fetch` by default. */\n    fetch?: typeof fetch | undefined;\n    /** Cancels the download. */\n    signal?: AbortSignal | undefined;\n}\n\n/**\n * Download a hosted dataset and decode it.\n * @param name - the dataset name: lowercase letters, digits and dashes\n * @param options - the base URL, fetch implementation and abort signal\n * @returns the graph as a frozen graph-format snapshot\n */\nexport async function fetchDataset(name: string, options: FetchDatasetOptions = {}): Promise<GraphSnapshot> {\n    if (!/^[a-z0-9][a-z0-9-]*$/.test(name)) {\n        throw new RangeError(`not a dataset name: ${JSON.stringify(name)}`);\n    }\n    const base = options.baseUrl ?? DEFAULT_DATASET_BASE_URL;\n    const url = new URL(`${name}.gsnp.gz`, base.endsWith(\"/\") ? base : `${base}/`);\n    const response = await (options.fetch ?? fetch)(url, { signal: options.signal ?? null });\n    if (!response.ok || response.body === null) {\n        throw new Error(`fetching ${url.href} failed: HTTP ${response.status}`);\n    }\n    const unzipped = response.body.pipeThrough(new DecompressionStream(\"gzip\"));\n    return fromBytes(new Uint8Array(await new Response(unzipped).arrayBuffer()));\n}\n","/**\n * Records for graphty-element's `nodeData` / `edgeData` properties.\n */\n\nimport { type SampleGraph } from \"./types.js\";\n\n/** The node and edge records graphty-element loads. */\nexport interface ElementData {\n    /** One record per node: `id` plus one field per node column. */\n    readonly nodes: Record<string, unknown>[];\n    /** One record per edge: `source`, `target` and, when weighted, `weight`. */\n    readonly edges: Record<string, unknown>[];\n}\n\n/**\n * Turn a graph into the plain records `<graphty-element>` takes as `nodeData` and `edgeData`.\n * A node's id is its external id when the graph has them, else its index. Builds one object per\n * node and edge, so it is meant for graphs a browser draws, not for millions of edges.\n * @param graph - a generator's or dataset's graph\n * @returns the node and edge records\n */\nexport function toElementData(graph: SampleGraph): ElementData {\n    const { ids, src, dst, weights } = graph;\n    const columns = Object.entries(graph.nodeColumns ?? {}).map(\n        ([name, column]) => [name, ArrayBuffer.isView(column) ? column : column.data] as const,\n    );\n    const idOf = (i: number): string | number => (ids === undefined ? i : ids[i]);\n    const nodes = Array.from({ length: graph.nodeCount }, (_, i) => {\n        const record: Record<string, unknown> = { id: idOf(i) };\n        for (const [name, data] of columns) {\n            record[name] = data[i];\n        }\n        return record;\n    });\n    const edges = Array.from(src, (u, e) =>\n        weights === undefined\n            ? { source: idOf(u), target: idOf(dst[e]) }\n            : { source: idOf(u), target: idOf(dst[e]), weight: weights[e] },\n    );\n    return { nodes, edges };\n}\n"],"names":[],"mappings":";;;;;;;;;;;;;AAQO,MAAM,kBAA0C;AAAA,EACnD;AAAA,IACI,MAAM;AAAA,IACN,OAAO;AAAA,IACP,aACI;AAAA,IACJ,UACI;AAAA,IACJ,QAAQ;AAAA,IACR,SACI;AAAA,IACJ,OAAO;AAAA,IACP,OAAO;AAAA,IACP,UAAU;AAAA,IACV,UAAU;AAAA,IACV,YAAY;AAAA,MACR,WAAW;AAAA,MACX,UAAU;AAAA,IAAA;AAAA,IAEd,aAAa;AAAA,IACb,WAAW;AAAA,MACP;AAAA,MACA;AAAA,MACA;AAAA,IAAA;AAAA,IAEJ,SAAS;AAAA,IACT,OAAO;AAAA,IACP,QAAQ;AAAA,EAAA;AAAA,EAEZ;AAAA,IACI,MAAM;AAAA,IACN,OAAO;AAAA,IACP,aACI;AAAA,IACJ,UACI;AAAA,IACJ,QAAQ;AAAA,IACR,SAAS;AAAA,IACT,OAAO;AAAA,IACP,OAAO;AAAA,IACP,UAAU;AAAA,IACV,UAAU;AAAA,IACV,YAAY;AAAA,MACR,MAAM;AAAA,MACN,SAAS;AAAA,IAAA;AAAA,IAEb,aAAa;AAAA,IACb,WAAW;AAAA,MACP;AAAA,MACA;AAAA,MACA;AAAA,IAAA;AAAA,IAEJ,SAAS;AAAA,IACT,OAAO;AAAA,IACP,QAAQ;AAAA,EAAA;AAAA,EAEZ;AAAA,IACI,MAAM;AAAA,IACN,OAAO;AAAA,IACP,aACI;AAAA,IACJ,UACI;AAAA,IACJ,QAAQ;AAAA,IACR,SACI;AAAA,IACJ,OAAO;AAAA,IACP,OAAO;AAAA,IACP,UAAU;AAAA,IACV,UAAU;AAAA,IACV,YAAY,CAAA;AAAA,IACZ,aAAa;AAAA,IACb,WAAW;AAAA,MACP;AAAA,MACA;AAAA,MACA;AAAA,IAAA;AAAA,IAEJ,SAAS;AAAA,IACT,OAAO;AAAA,IACP,QAAQ;AAAA,EAAA;AAEhB;ACrEO,MAAM,WAAmC;AAAA,EAC5C;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA,GAAG;AACP;ACvBO,MAAM,2BAA2B;AAkBxC,eAAsB,aAAa,MAAc,UAA+B,IAA4B;AACxG,MAAI,CAAC,uBAAuB,KAAK,IAAI,GAAG;AACpC,UAAM,IAAI,WAAW,uBAAuB,KAAK,UAAU,IAAI,CAAC,EAAE;AAAA,EACtE;AACA,QAAM,OAAO,QAAQ,WAAW;AAChC,QAAM,MAAM,IAAI,IAAI,GAAG,IAAI,YAAY,KAAK,SAAS,GAAG,IAAI,OAAO,GAAG,IAAI,GAAG;AAC7E,QAAM,WAAW,OAAO,QAAQ,SAAS,OAAO,KAAK,EAAE,QAAQ,QAAQ,UAAU,KAAA,CAAM;AACvF,MAAI,CAAC,SAAS,MAAM,SAAS,SAAS,MAAM;AACxC,UAAM,IAAI,MAAM,YAAY,IAAI,IAAI,iBAAiB,SAAS,MAAM,EAAE;AAAA,EAC1E;AACA,QAAM,WAAW,SAAS,KAAK,YAAY,IAAI,oBAAoB,MAAM,CAAC;AAC1E,SAAO,UAAU,IAAI,WAAW,MAAM,IAAI,SAAS,QAAQ,EAAE,YAAA,CAAa,CAAC;AAC/E;ACpBO,SAAS,cAAc,OAAiC;AAC3D,QAAM,EAAE,KAAK,KAAK,KAAK,YAAY;AACnC,QAAM,UAAU,OAAO,QAAQ,MAAM,eAAe,CAAA,CAAE,EAAE;AAAA,IACpD,CAAC,CAAC,MAAM,MAAM,MAAM,CAAC,MAAM,YAAY,OAAO,MAAM,IAAI,SAAS,OAAO,IAAI;AAAA,EAAA;AAEhF,QAAM,OAAO,CAAC,MAAgC,QAAQ,SAAY,IAAI,IAAI,CAAC;AAC3E,QAAM,QAAQ,MAAM,KAAK,EAAE,QAAQ,MAAM,UAAA,GAAa,CAAC,GAAG,MAAM;AAC5D,UAAM,SAAkC,EAAE,IAAI,KAAK,CAAC,EAAA;AACpD,eAAW,CAAC,MAAM,IAAI,KAAK,SAAS;AAChC,aAAO,IAAI,IAAI,KAAK,CAAC;AAAA,IACzB;AACA,WAAO;AAAA,EACX,CAAC;AACD,QAAM,QAAQ,MAAM;AAAA,IAAK;AAAA,IAAK,CAAC,GAAG,MAC9B,YAAY,SACN,EAAE,QAAQ,KAAK,CAAC,GAAG,QAAQ,KAAK,IAAI,CAAC,CAAC,EAAA,IACtC,EAAE,QAAQ,KAAK,CAAC,GAAG,QAAQ,KAAK,IAAI,CAAC,CAAC,GAAG,QAAQ,QAAQ,CAAC,EAAA;AAAA,EAAE;AAEtE,SAAO,EAAE,OAAO,MAAA;AACpB;"}

package/dist/src/datasets/build.d.ts

@@ -0,0 +1,89 @@
+/**
+ * The shapes shared by every dataset module: its metadata, the compact form its generated data
+ * file is written in, and the one function that turns that form into a {@link SampleGraph}.
+ */
+import { type SampleGraph } from "../types.js";
+/** What a dataset is, where it came from and under which terms. */
+export interface DatasetMeta {
+    /** The subpath name: `@graphty/graph-samples/datasets/<name>`. */
+    readonly name: string;
+    /** The human-readable title. */
+    readonly title: string;
+    /** One or two sentences on what the nodes and edges are. */
+    readonly description: string;
+    /** The reference to cite. */
+    readonly citation: string;
+    /** The URL the data was converted from. */
+    readonly source: string;
+    /** The license as known, or "unclear" with what is known. */
+    readonly license: string;
+    /** The node count. */
+    readonly nodes: number;
+    /** The edge count. */
+    readonly edges: number;
+    /** Whether the edges are directed. */
+    readonly directed: boolean;
+    /** Whether the edges carry weights. */
+    readonly weighted: boolean;
+    /** The node columns, name to description. */
+    readonly attributes: Readonly<Record<string, string>>;
+    /** The node column holding the ground-truth grouping, or null when there is none. */
+    readonly groundTruth: string | null;
+    /** The algorithms and layouts it shows off. */
+    readonly showcases: readonly string[];
+    /**
+     * Where the graph data lives: "bundled" (the subpath `@graphty/graph-samples/datasets/<name>`;
+     * the meaning when absent) or "remote" (on graphty.app, loaded with `fetchDataset(name)`).
+     */
+    readonly hosting?: "bundled" | "remote";
+    /** A remote dataset's download size: the bytes of its `.gsnp.gz` file. */
+    readonly bytes?: number;
+    /** A remote dataset's checksum: the SHA-256 of its `.gsnp.gz` file, lowercase hex. */
+    readonly sha256?: string;
+}
+/** A categorical column: codes into a list of category names. */
+interface DictColumnData {
+    readonly dtype: "dict";
+    readonly categories: readonly string[];
+    readonly codes: readonly number[];
+}
+/** A text column, e.g. the display label. */
+interface StringColumnData {
+    readonly dtype: "string";
+    readonly role?: "label";
+    readonly values: readonly string[];
+}
+/** A small unsigned integer column, e.g. a bipartite side. */
+interface U8ColumnData {
+    readonly dtype: "u8";
+    readonly values: readonly number[];
+}
+/** A number column, e.g. a latitude. */
+interface F64ColumnData {
+    readonly dtype: "f64";
+    readonly values: readonly number[];
+}
+/** An unsigned 32-bit integer column, e.g. a population. */
+interface U32ColumnData {
+    readonly dtype: "u32";
+    readonly values: readonly number[];
+}
+/** The compact form of a dataset, as scripts/convert-datasets.mjs writes it into data.ts. */
+export interface DatasetData {
+    readonly directed: boolean;
+    readonly nodeCount: number;
+    /** External node ids in index order, or null when the index is the id. */
+    readonly ids: readonly string[] | null;
+    /** Flat edge endpoints: src0, dst0, src1, dst1, ... */
+    readonly edges: readonly number[];
+    readonly weights: readonly number[] | null;
+    readonly columns: Readonly<Record<string, DictColumnData | StringColumnData | U8ColumnData | F64ColumnData | U32ColumnData>>;
+}
+/**
+ * Expand a dataset's compact data into typed arrays and graph-format column inputs.
+ * @param data - the generated data
+ * @returns the graph
+ */
+export declare function buildDataset(data: DatasetData): SampleGraph;
+export {};
+//# sourceMappingURL=build.d.ts.map

package/dist/src/datasets/build.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"build.d.ts","sourceRoot":"","sources":["../../../src/datasets/build.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAIH,OAAO,EAAE,KAAK,WAAW,EAAE,MAAM,aAAa,CAAC;AAE/C,mEAAmE;AACnE,MAAM,WAAW,WAAW;IACxB,kEAAkE;IAClE,QAAQ,CAAC,IAAI,EAAE,MAAM,CAAC;IACtB,gCAAgC;IAChC,QAAQ,CAAC,KAAK,EAAE,MAAM,CAAC;IACvB,4DAA4D;IAC5D,QAAQ,CAAC,WAAW,EAAE,MAAM,CAAC;IAC7B,6BAA6B;IAC7B,QAAQ,CAAC,QAAQ,EAAE,MAAM,CAAC;IAC1B,2CAA2C;IAC3C,QAAQ,CAAC,MAAM,EAAE,MAAM,CAAC;IACxB,6DAA6D;IAC7D,QAAQ,CAAC,OAAO,EAAE,MAAM,CAAC;IACzB,sBAAsB;IACtB,QAAQ,CAAC,KAAK,EAAE,MAAM,CAAC;IACvB,sBAAsB;IACtB,QAAQ,CAAC,KAAK,EAAE,MAAM,CAAC;IACvB,sCAAsC;IACtC,QAAQ,CAAC,QAAQ,EAAE,OAAO,CAAC;IAC3B,uCAAuC;IACvC,QAAQ,CAAC,QAAQ,EAAE,OAAO,CAAC;IAC3B,6CAA6C;IAC7C,QAAQ,CAAC,UAAU,EAAE,QAAQ,CAAC,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC,CAAC;IACtD,qFAAqF;IACrF,QAAQ,CAAC,WAAW,EAAE,MAAM,GAAG,IAAI,CAAC;IACpC,+CAA+C;IAC/C,QAAQ,CAAC,SAAS,EAAE,SAAS,MAAM,EAAE,CAAC;IACtC;;;OAGG;IACH,QAAQ,CAAC,OAAO,CAAC,EAAE,SAAS,GAAG,QAAQ,CAAC;IACxC,0EAA0E;IAC1E,QAAQ,CAAC,KAAK,CAAC,EAAE,MAAM,CAAC;IACxB,sFAAsF;IACtF,QAAQ,CAAC,MAAM,CAAC,EAAE,MAAM,CAAC;CAC5B;AAED,iEAAiE;AACjE,UAAU,cAAc;IACpB,QAAQ,CAAC,KAAK,EAAE,MAAM,CAAC;IACvB,QAAQ,CAAC,UAAU,EAAE,SAAS,MAAM,EAAE,CAAC;IACvC,QAAQ,CAAC,KAAK,EAAE,SAAS,MAAM,EAAE,CAAC;CACrC;AAED,6CAA6C;AAC7C,UAAU,gBAAgB;IACtB,QAAQ,CAAC,KAAK,EAAE,QAAQ,CAAC;IACzB,QAAQ,CAAC,IAAI,CAAC,EAAE,OAAO,CAAC;IACxB,QAAQ,CAAC,MAAM,EAAE,SAAS,MAAM,EAAE,CAAC;CACtC;AAED,8DAA8D;AAC9D,UAAU,YAAY;IAClB,QAAQ,CAAC,KAAK,EAAE,IAAI,CAAC;IACrB,QAAQ,CAAC,MAAM,EAAE,SAAS,MAAM,EAAE,CAAC;CACtC;AAED,wCAAwC;AACxC,UAAU,aAAa;IACnB,QAAQ,CAAC,KAAK,EAAE,KAAK,CAAC;IACtB,QAAQ,CAAC,MAAM,EAAE,SAAS,MAAM,EAAE,CAAC;CACtC;AAED,4DAA4D;AAC5D,UAAU,aAAa;IACnB,QAAQ,CAAC,KAAK,EAAE,KAAK,CAAC;IACtB,QAAQ,CAAC,MAAM,EAAE,SAAS,MAAM,EAAE,CAAC;CACtC;AAED,6FAA6F;AAC7F,MAAM,WAAW,WAAW;IACxB,QAAQ,CAAC,QAAQ,EAAE,OAAO,CAAC;IAC3B,QAAQ,CAAC,SAAS,EAAE,MAAM,CAAC;IAC3B,0EAA0E;IAC1E,QAAQ,CAAC,GAAG,EAAE,SAAS,MAAM,EAAE,GAAG,IAAI,CAAC;IACvC,uDAAuD;IACvD,QAAQ,CAAC,KAAK,EAAE,SAAS,MAAM,EAAE,CAAC;IAClC,QAAQ,CAAC,OAAO,EAAE,SAAS,MAAM,EAAE,GAAG,IAAI,CAAC;IAC3C,QAAQ,CAAC,OAAO,EAAE,QAAQ,CAAC,MAAM,CAAC,MAAM,EAAE,cAAc,GAAG,gBAAgB,GAAG,YAAY,GAAG,aAAa,GAAG,aAAa,CAAC,CAAC,CAAC;CAChI;AAED;;;;GAIG;AACH,wBAAgB,YAAY,CAAC,IAAI,EAAE,WAAW,GAAG,WAAW,CA0C3D"}

package/dist/src/datasets/build.js

@@ -0,0 +1,53 @@
+/**
+ * The shapes shared by every dataset module: its metadata, the compact form its generated data
+ * file is written in, and the one function that turns that form into a {@link SampleGraph}.
+ */
+/**
+ * Expand a dataset's compact data into typed arrays and graph-format column inputs.
+ * @param data - the generated data
+ * @returns the graph
+ */
+export function buildDataset(data) {
+    const m = data.edges.length / 2;
+    const src = new Uint32Array(m);
+    const dst = new Uint32Array(m);
+    for (let e = 0; e < m; e++) {
+        src[e] = data.edges[2 * e];
+        dst[e] = data.edges[2 * e + 1];
+    }
+    const nodeColumns = {};
+    for (const [name, column] of Object.entries(data.columns)) {
+        switch (column.dtype) {
+            case "dict":
+                nodeColumns[name] = {
+                    data: column.codes.map((code) => column.categories[code]),
+                    decl: { dtype: "dict", options: column.categories },
+                };
+                break;
+            case "string":
+                nodeColumns[name] = { data: column.values, decl: { dtype: "string", role: column.role } };
+                break;
+            case "u8":
+                nodeColumns[name] = Uint8Array.from(column.values);
+                break;
+            case "u32":
+                nodeColumns[name] = Uint32Array.from(column.values);
+                break;
+            case "f64":
+                nodeColumns[name] = Float64Array.from(column.values);
+                break;
+            default:
+                throw new TypeError(`unknown column dtype in dataset column "${name}"`);
+        }
+    }
+    return {
+        directed: data.directed,
+        nodeCount: data.nodeCount,
+        src,
+        dst,
+        ...(data.weights === null ? {} : { weights: Float32Array.from(data.weights) }),
+        ...(data.ids === null ? {} : { ids: data.ids }),
+        ...(Object.keys(nodeColumns).length === 0 ? {} : { nodeColumns }),
+    };
+}
+//# sourceMappingURL=build.js.map

package/dist/src/datasets/build.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"build.js","sourceRoot":"","sources":["../../../src/datasets/build.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAyFH;;;;GAIG;AACH,MAAM,UAAU,YAAY,CAAC,IAAiB;IAC1C,MAAM,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,MAAM,GAAG,CAAC,CAAC;IAChC,MAAM,GAAG,GAAG,IAAI,WAAW,CAAC,CAAC,CAAC,CAAC;IAC/B,MAAM,GAAG,GAAG,IAAI,WAAW,CAAC,CAAC,CAAC,CAAC;IAC/B,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC;QACzB,GAAG,CAAC,CAAC,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC;QAC3B,GAAG,CAAC,CAAC,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC,CAAC;IACnC,CAAC;IACD,MAAM,WAAW,GAAiD,EAAE,CAAC;IACrE,KAAK,MAAM,CAAC,IAAI,EAAE,MAAM,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,IAAI,CAAC,OAAO,CAAC,EAAE,CAAC;QACxD,QAAQ,MAAM,CAAC,KAAK,EAAE,CAAC;YACnB,KAAK,MAAM;gBACP,WAAW,CAAC,IAAI,CAAC,GAAG;oBAChB,IAAI,EAAE,MAAM,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,MAAM,CAAC,UAAU,CAAC,IAAI,CAAC,CAAC;oBACzD,IAAI,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,CAAC,UAAU,EAAE;iBACtD,CAAC;gBACF,MAAM;YACV,KAAK,QAAQ;gBACT,WAAW,CAAC,IAAI,CAAC,GAAG,EAAE,IAAI,EAAE,MAAM,CAAC,MAAM,EAAE,IAAI,EAAE,EAAE,KAAK,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,CAAC,IAAI,EAAE,EAAE,CAAC;gBAC1F,MAAM;YACV,KAAK,IAAI;gBACL,WAAW,CAAC,IAAI,CAAC,GAAG,UAAU,CAAC,IAAI,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC;gBACnD,MAAM;YACV,KAAK,KAAK;gBACN,WAAW,CAAC,IAAI,CAAC,GAAG,WAAW,CAAC,IAAI,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC;gBACpD,MAAM;YACV,KAAK,KAAK;gBACN,WAAW,CAAC,IAAI,CAAC,GAAG,YAAY,CAAC,IAAI,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC;gBACrD,MAAM;YACV;gBACI,MAAM,IAAI,SAAS,CAAC,2CAA2C,IAAI,GAAG,CAAC,CAAC;QAChF,CAAC;IACL,CAAC;IACD,OAAO;QACH,QAAQ,EAAE,IAAI,CAAC,QAAQ;QACvB,SAAS,EAAE,IAAI,CAAC,SAAS;QACzB,GAAG;QACH,GAAG;QACH,GAAG,CAAC,IAAI,CAAC,OAAO,KAAK,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,OAAO,EAAE,YAAY,CAAC,IAAI,CAAC,IAAI,CAAC,OAAO,CAAC,EAAE,CAAC;QAC9E,GAAG,CAAC,IAAI,CAAC,GAAG,KAAK,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,GAAG,EAAE,IAAI,CAAC,GAAG,EAAE,CAAC;QAC/C,GAAG,CAAC,MAAM,CAAC,IAAI,CAAC,WAAW,CAAC,CAAC,MAAM,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,WAAW,EAAE,CAAC;KACpE,CAAC;AACN,CAAC"}

package/dist/src/datasets/catalog.d.ts

@@ -0,0 +1,8 @@
+import { type DatasetMeta } from "./build.js";
+/**
+ * The metadata of every dataset (no graph data). A bundled dataset's edges load only from its own
+ * subpath, `@graphty/graph-samples/datasets/<name>`; a dataset with `hosting: "remote"` loads with
+ * `fetchDataset(name)`.
+ */
+export declare const DATASETS: readonly DatasetMeta[];
+//# sourceMappingURL=catalog.d.ts.map

package/dist/src/datasets/catalog.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"catalog.d.ts","sourceRoot":"","sources":["../../../src/datasets/catalog.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,KAAK,WAAW,EAAE,MAAM,YAAY,CAAC;AAe9C;;;;GAIG;AACH,eAAO,MAAM,QAAQ,EAAE,SAAS,WAAW,EAc1C,CAAC"}

package/dist/src/datasets/catalog.js

@@ -0,0 +1,34 @@
+import { celegansNeuralMeta } from "./celegans-neural/meta.js";
+import { contiguousUsaMeta } from "./contiguous-usa/meta.js";
+import { davisSouthernWomenMeta } from "./davis-southern-women/meta.js";
+import { dolphinsMeta } from "./dolphins/meta.js";
+import { florentineFamiliesMeta } from "./florentine-families/meta.js";
+import { footballMeta } from "./football/meta.js";
+import { HOSTED_DATASETS } from "./hosted.js";
+import { karateMeta } from "./karate/meta.js";
+import { knuthMilesMeta } from "./knuth-miles/meta.js";
+import { lesMiserablesMeta } from "./les-miserables/meta.js";
+import { openflightsMeta } from "./openflights/meta.js";
+import { politicalBlogsMeta } from "./political-blogs/meta.js";
+import { politicalBooksMeta } from "./political-books/meta.js";
+/**
+ * The metadata of every dataset (no graph data). A bundled dataset's edges load only from its own
+ * subpath, `@graphty/graph-samples/datasets/<name>`; a dataset with `hosting: "remote"` loads with
+ * `fetchDataset(name)`.
+ */
+export const DATASETS = [
+    karateMeta,
+    florentineFamiliesMeta,
+    davisSouthernWomenMeta,
+    lesMiserablesMeta,
+    footballMeta,
+    politicalBooksMeta,
+    dolphinsMeta,
+    contiguousUsaMeta,
+    knuthMilesMeta,
+    celegansNeuralMeta,
+    politicalBlogsMeta,
+    openflightsMeta,
+    ...HOSTED_DATASETS,
+];
+//# sourceMappingURL=catalog.js.map

package/dist/src/datasets/catalog.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"catalog.js","sourceRoot":"","sources":["../../../src/datasets/catalog.ts"],"names":[],"mappings":"AACA,OAAO,EAAE,kBAAkB,EAAE,MAAM,2BAA2B,CAAC;AAC/D,OAAO,EAAE,iBAAiB,EAAE,MAAM,0BAA0B,CAAC;AAC7D,OAAO,EAAE,sBAAsB,EAAE,MAAM,gCAAgC,CAAC;AACxE,OAAO,EAAE,YAAY,EAAE,MAAM,oBAAoB,CAAC;AAClD,OAAO,EAAE,sBAAsB,EAAE,MAAM,+BAA+B,CAAC;AACvE,OAAO,EAAE,YAAY,EAAE,MAAM,oBAAoB,CAAC;AAClD,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAC;AAC9C,OAAO,EAAE,UAAU,EAAE,MAAM,kBAAkB,CAAC;AAC9C,OAAO,EAAE,cAAc,EAAE,MAAM,uBAAuB,CAAC;AACvD,OAAO,EAAE,iBAAiB,EAAE,MAAM,0BAA0B,CAAC;AAC7D,OAAO,EAAE,eAAe,EAAE,MAAM,uBAAuB,CAAC;AACxD,OAAO,EAAE,kBAAkB,EAAE,MAAM,2BAA2B,CAAC;AAC/D,OAAO,EAAE,kBAAkB,EAAE,MAAM,2BAA2B,CAAC;AAE/D;;;;GAIG;AACH,MAAM,CAAC,MAAM,QAAQ,GAA2B;IAC5C,UAAU;IACV,sBAAsB;IACtB,sBAAsB;IACtB,iBAAiB;IACjB,YAAY;IACZ,kBAAkB;IAClB,YAAY;IACZ,iBAAiB;IACjB,cAAc;IACd,kBAAkB;IAClB,kBAAkB;IAClB,eAAe;IACf,GAAG,eAAe;CACrB,CAAC"}

package/dist/src/datasets/celegans-neural/data.d.ts

@@ -0,0 +1,3 @@
+import { type DatasetData } from "../build.js";
+export declare const DATA: DatasetData;
+//# sourceMappingURL=data.d.ts.map

package/dist/src/datasets/celegans-neural/data.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"data.d.ts","sourceRoot":"","sources":["../../../../src/datasets/celegans-neural/data.ts"],"names":[],"mappings":"AAIA,OAAO,EAAE,KAAK,WAAW,EAAE,MAAM,aAAa,CAAC;AAE/C,eAAO,MAAM,IAAI,EAAE,WAwjBlB,CAAC"}