@zenalexa/unicli 0.225.1 → 0.225.3
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/AGENTS.md +3 -3
- package/README.md +3 -3
- package/README.zh-CN.md +3 -3
- package/dist/adapters/acl-anthology/papers.d.ts +16 -9
- package/dist/adapters/acl-anthology/papers.d.ts.map +1 -1
- package/dist/adapters/acl-anthology/papers.js +322 -58
- package/dist/adapters/acl-anthology/papers.js.map +1 -1
- package/dist/adapters/arxiv/papers.d.ts +22 -4
- package/dist/adapters/arxiv/papers.d.ts.map +1 -1
- package/dist/adapters/arxiv/papers.js +202 -4
- package/dist/adapters/arxiv/papers.js.map +1 -1
- package/dist/adapters/baidu-scholar/search.d.ts +15 -1
- package/dist/adapters/baidu-scholar/search.d.ts.map +1 -1
- package/dist/adapters/baidu-scholar/search.js +72 -8
- package/dist/adapters/baidu-scholar/search.js.map +1 -1
- package/dist/adapters/biorxiv/preprints.d.ts +9 -0
- package/dist/adapters/biorxiv/preprints.d.ts.map +1 -0
- package/dist/adapters/biorxiv/preprints.js +78 -0
- package/dist/adapters/biorxiv/preprints.js.map +1 -0
- package/dist/adapters/cnki/search.d.ts +82 -0
- package/dist/adapters/cnki/search.d.ts.map +1 -0
- package/dist/adapters/cnki/search.js +236 -0
- package/dist/adapters/cnki/search.js.map +1 -0
- package/dist/adapters/cvf/papers.d.ts +12 -7
- package/dist/adapters/cvf/papers.d.ts.map +1 -1
- package/dist/adapters/cvf/papers.js +210 -27
- package/dist/adapters/cvf/papers.js.map +1 -1
- package/dist/adapters/dblp/publications.d.ts +12 -5
- package/dist/adapters/dblp/publications.d.ts.map +1 -1
- package/dist/adapters/dblp/publications.js +31 -8
- package/dist/adapters/dblp/publications.js.map +1 -1
- package/dist/adapters/google-scholar/search.d.ts +22 -1
- package/dist/adapters/google-scholar/search.d.ts.map +1 -1
- package/dist/adapters/google-scholar/search.js +129 -14
- package/dist/adapters/google-scholar/search.js.map +1 -1
- package/dist/adapters/hf/paper.d.ts +12 -3
- package/dist/adapters/hf/paper.d.ts.map +1 -1
- package/dist/adapters/hf/paper.js +65 -5
- package/dist/adapters/hf/paper.js.map +1 -1
- package/dist/adapters/medrxiv/preprints.d.ts +9 -0
- package/dist/adapters/medrxiv/preprints.d.ts.map +1 -0
- package/dist/adapters/medrxiv/preprints.js +78 -0
- package/dist/adapters/medrxiv/preprints.js.map +1 -0
- package/dist/adapters/neurips/proceedings.d.ts +8 -7
- package/dist/adapters/neurips/proceedings.d.ts.map +1 -1
- package/dist/adapters/neurips/proceedings.js +209 -21
- package/dist/adapters/neurips/proceedings.js.map +1 -1
- package/dist/adapters/openalex/works.d.ts +21 -5
- package/dist/adapters/openalex/works.d.ts.map +1 -1
- package/dist/adapters/openalex/works.js +108 -8
- package/dist/adapters/openalex/works.js.map +1 -1
- package/dist/adapters/openreview/papers.d.ts +10 -4
- package/dist/adapters/openreview/papers.d.ts.map +1 -1
- package/dist/adapters/openreview/papers.js +351 -24
- package/dist/adapters/openreview/papers.js.map +1 -1
- package/dist/adapters/pmlr/proceedings.d.ts +6 -6
- package/dist/adapters/pmlr/proceedings.d.ts.map +1 -1
- package/dist/adapters/pmlr/proceedings.js +92 -12
- package/dist/adapters/pmlr/proceedings.js.map +1 -1
- package/dist/adapters/pubmed/articles.d.ts +8 -4
- package/dist/adapters/pubmed/articles.d.ts.map +1 -1
- package/dist/adapters/pubmed/articles.js +272 -39
- package/dist/adapters/pubmed/articles.js.map +1 -1
- package/dist/adapters/rxiv/preprints.d.ts +75 -0
- package/dist/adapters/rxiv/preprints.d.ts.map +1 -0
- package/dist/adapters/rxiv/preprints.js +651 -0
- package/dist/adapters/rxiv/preprints.js.map +1 -0
- package/dist/adapters/scholar-artifacts/pdf-read.d.ts +49 -0
- package/dist/adapters/scholar-artifacts/pdf-read.d.ts.map +1 -0
- package/dist/adapters/scholar-artifacts/pdf-read.js +204 -0
- package/dist/adapters/scholar-artifacts/pdf-read.js.map +1 -0
- package/dist/adapters/scholar-artifacts/pdf.d.ts +16 -0
- package/dist/adapters/scholar-artifacts/pdf.d.ts.map +1 -0
- package/dist/adapters/scholar-artifacts/pdf.js +122 -0
- package/dist/adapters/scholar-artifacts/pdf.js.map +1 -0
- package/dist/adapters/semantic-scholar/papers.d.ts +6 -6
- package/dist/adapters/semantic-scholar/papers.d.ts.map +1 -1
- package/dist/adapters/semantic-scholar/papers.js +80 -6
- package/dist/adapters/semantic-scholar/papers.js.map +1 -1
- package/dist/adapters/unpaywall/works.d.ts +7 -7
- package/dist/adapters/unpaywall/works.d.ts.map +1 -1
- package/dist/adapters/unpaywall/works.js +104 -12
- package/dist/adapters/unpaywall/works.js.map +1 -1
- package/dist/adapters/wanfang/search.d.ts +14 -0
- package/dist/adapters/wanfang/search.d.ts.map +1 -1
- package/dist/adapters/wanfang/search.js +56 -7
- package/dist/adapters/wanfang/search.js.map +1 -1
- package/dist/browser/page.d.ts +2 -0
- package/dist/browser/page.d.ts.map +1 -1
- package/dist/browser/page.js +12 -0
- package/dist/browser/page.js.map +1 -1
- package/dist/browser/protocol.d.ts +6 -1
- package/dist/browser/protocol.d.ts.map +1 -1
- package/dist/browser/protocol.js.map +1 -1
- package/dist/commands/browser/actions.d.ts.map +1 -1
- package/dist/commands/browser/actions.js +487 -8
- package/dist/commands/browser/actions.js.map +1 -1
- package/dist/commands/compute.js +12 -1
- package/dist/commands/compute.js.map +1 -1
- package/dist/commands/schema.d.ts.map +1 -1
- package/dist/commands/schema.js +22 -0
- package/dist/commands/schema.js.map +1 -1
- package/dist/commands/scholar.d.ts +77 -5
- package/dist/commands/scholar.d.ts.map +1 -1
- package/dist/commands/scholar.js +2945 -83
- package/dist/commands/scholar.js.map +1 -1
- package/dist/commands/search.d.ts.map +1 -1
- package/dist/commands/search.js +14 -3
- package/dist/commands/search.js.map +1 -1
- package/dist/compute/contracts.d.ts +55 -0
- package/dist/compute/contracts.d.ts.map +1 -0
- package/dist/compute/contracts.js +487 -0
- package/dist/compute/contracts.js.map +1 -0
- package/dist/core/command-contract.d.ts.map +1 -1
- package/dist/core/command-contract.js +5 -0
- package/dist/core/command-contract.js.map +1 -1
- package/dist/core/schema-v2.d.ts +1 -0
- package/dist/core/schema-v2.d.ts.map +1 -1
- package/dist/core/schema-v2.js +1 -0
- package/dist/core/schema-v2.js.map +1 -1
- package/dist/discovery/aliases.d.ts +8 -1
- package/dist/discovery/aliases.d.ts.map +1 -1
- package/dist/discovery/aliases.js +333 -20
- package/dist/discovery/aliases.js.map +1 -1
- package/dist/discovery/core-catalog.d.ts +2 -0
- package/dist/discovery/core-catalog.d.ts.map +1 -1
- package/dist/discovery/core-catalog.js +525 -66
- package/dist/discovery/core-catalog.js.map +1 -1
- package/dist/discovery/intents.d.ts +1 -0
- package/dist/discovery/intents.d.ts.map +1 -1
- package/dist/discovery/intents.js +299 -2
- package/dist/discovery/intents.js.map +1 -1
- package/dist/discovery/loader.d.ts.map +1 -1
- package/dist/discovery/loader.js +3 -0
- package/dist/discovery/loader.js.map +1 -1
- package/dist/discovery/macos-dynamic.d.ts +1 -0
- package/dist/discovery/macos-dynamic.d.ts.map +1 -1
- package/dist/discovery/macos-dynamic.js +20 -1
- package/dist/discovery/macos-dynamic.js.map +1 -1
- package/dist/discovery/search.d.ts.map +1 -1
- package/dist/discovery/search.js +12 -5
- package/dist/discovery/search.js.map +1 -1
- package/dist/engine/browser/evidence.d.ts +34 -1
- package/dist/engine/browser/evidence.d.ts.map +1 -1
- package/dist/engine/browser/evidence.js +141 -6
- package/dist/engine/browser/evidence.js.map +1 -1
- package/dist/engine/capability-policy.d.ts.map +1 -1
- package/dist/engine/capability-policy.js +30 -4
- package/dist/engine/capability-policy.js.map +1 -1
- package/dist/engine/kernel/stages.d.ts.map +1 -1
- package/dist/engine/kernel/stages.js +3 -0
- package/dist/engine/kernel/stages.js.map +1 -1
- package/dist/engine/operation-policy.d.ts +4 -1
- package/dist/engine/operation-policy.d.ts.map +1 -1
- package/dist/engine/operation-policy.js +23 -0
- package/dist/engine/operation-policy.js.map +1 -1
- package/dist/engine/steps/fetch-text.d.ts.map +1 -1
- package/dist/engine/steps/fetch-text.js +2 -2
- package/dist/engine/steps/fetch-text.js.map +1 -1
- package/dist/engine/steps/fetch.d.ts +1 -0
- package/dist/engine/steps/fetch.d.ts.map +1 -1
- package/dist/engine/steps/fetch.js +24 -4
- package/dist/engine/steps/fetch.js.map +1 -1
- package/dist/fast-path/handlers/discovery.d.ts +5 -5
- package/dist/fast-path/handlers/discovery.d.ts.map +1 -1
- package/dist/fast-path/handlers/discovery.js +61 -8
- package/dist/fast-path/handlers/discovery.js.map +1 -1
- package/dist/fast-path/manifest.d.ts +3 -0
- package/dist/fast-path/manifest.d.ts.map +1 -1
- package/dist/fast-path/manifest.js.map +1 -1
- package/dist/fast-path/policy.d.ts.map +1 -1
- package/dist/fast-path/policy.js +3 -0
- package/dist/fast-path/policy.js.map +1 -1
- package/dist/fast-path/render.d.ts +2 -0
- package/dist/fast-path/render.d.ts.map +1 -1
- package/dist/fast-path/render.js +9 -0
- package/dist/fast-path/render.js.map +1 -1
- package/dist/manifest-compact.txt +2 -2
- package/dist/manifest.json +6977 -1002
- package/dist/mcp/handler.d.ts +2 -16
- package/dist/mcp/handler.d.ts.map +1 -1
- package/dist/mcp/handler.js.map +1 -1
- package/dist/mcp/http-transport.d.ts +7 -1
- package/dist/mcp/http-transport.d.ts.map +1 -1
- package/dist/mcp/http-transport.js +20 -1
- package/dist/mcp/http-transport.js.map +1 -1
- package/dist/mcp/jsonrpc.d.ts +27 -0
- package/dist/mcp/jsonrpc.d.ts.map +1 -0
- package/dist/mcp/jsonrpc.js +12 -0
- package/dist/mcp/jsonrpc.js.map +1 -0
- package/dist/mcp/origin-guard.d.ts +26 -0
- package/dist/mcp/origin-guard.d.ts.map +1 -0
- package/dist/mcp/origin-guard.js +42 -0
- package/dist/mcp/origin-guard.js.map +1 -0
- package/dist/mcp/profiles/computer-use.d.ts.map +1 -1
- package/dist/mcp/profiles/computer-use.js +30 -270
- package/dist/mcp/profiles/computer-use.js.map +1 -1
- package/dist/mcp/streamable-http/session.d.ts +4 -22
- package/dist/mcp/streamable-http/session.d.ts.map +1 -1
- package/dist/mcp/streamable-http/session.js +4 -24
- package/dist/mcp/streamable-http/session.js.map +1 -1
- package/dist/mcp/tools.d.ts.map +1 -1
- package/dist/mcp/tools.js +74 -54
- package/dist/mcp/tools.js.map +1 -1
- package/dist/output/envelope.d.ts +2 -0
- package/dist/output/envelope.d.ts.map +1 -1
- package/dist/output/envelope.js.map +1 -1
- package/dist/output/error-map.d.ts +14 -0
- package/dist/output/error-map.d.ts.map +1 -1
- package/dist/output/error-map.js +20 -0
- package/dist/output/error-map.js.map +1 -1
- package/dist/registry.d.ts +2 -0
- package/dist/registry.d.ts.map +1 -1
- package/dist/registry.js +1 -0
- package/dist/registry.js.map +1 -1
- package/dist/transport/cascade.d.ts.map +1 -1
- package/dist/transport/cascade.js +77 -5
- package/dist/transport/cascade.js.map +1 -1
- package/dist/transport/refs.d.ts +33 -1
- package/dist/transport/refs.d.ts.map +1 -1
- package/dist/transport/refs.js +40 -1
- package/dist/transport/refs.js.map +1 -1
- package/dist/types/scholarly.d.ts +19 -4
- package/dist/types/scholarly.d.ts.map +1 -1
- package/dist/types/scholarly.js +4 -4
- package/dist/types.d.ts +8 -0
- package/dist/types.d.ts.map +1 -1
- package/dist/types.js.map +1 -1
- package/package.json +1 -1
- package/server.json +2 -2
- package/skills/unicli/SKILL.md +1 -1
- package/skills/unicli-claude-code/SKILL.md +1 -1
- package/skills/unicli-hermes/SKILL.md +1 -1
- package/src/adapters/acl-anthology/papers.test.ts +111 -0
- package/src/adapters/acl-anthology/papers.ts +379 -71
- package/src/adapters/arxiv/papers.test.ts +46 -0
- package/src/adapters/arxiv/papers.ts +251 -4
- package/src/adapters/baidu-scholar/search.ts +74 -11
- package/src/adapters/biorxiv/preprints.ts +112 -0
- package/src/adapters/cnki/search.ts +357 -0
- package/src/adapters/cvf/papers.ts +260 -27
- package/src/adapters/dblp/publications.test.ts +9 -0
- package/src/adapters/dblp/publications.ts +31 -8
- package/src/adapters/defuddle/read.yaml +30 -0
- package/src/adapters/google-scholar/search.ts +165 -17
- package/src/adapters/hf/paper.test.ts +23 -0
- package/src/adapters/hf/paper.ts +89 -5
- package/src/adapters/hf/top.yaml +34 -2
- package/src/adapters/huggingface-papers/daily.yaml +37 -3
- package/src/adapters/huggingface-papers/search.yaml +43 -9
- package/src/adapters/jina/read.yaml +30 -0
- package/src/adapters/markdown-new/read.yaml +50 -0
- package/src/adapters/medrxiv/preprints.ts +112 -0
- package/src/adapters/neurips/proceedings.ts +266 -22
- package/src/adapters/ollama-cloud/fetch.yaml +39 -0
- package/src/adapters/ollama-cloud/search.yaml +43 -0
- package/src/adapters/openalex/works.test.ts +15 -4
- package/src/adapters/openalex/works.ts +136 -8
- package/src/adapters/openreview/papers.test.ts +31 -0
- package/src/adapters/openreview/papers.ts +407 -29
- package/src/adapters/pmlr/proceedings.ts +102 -12
- package/src/adapters/pubmed/articles.test.ts +88 -1
- package/src/adapters/pubmed/articles.ts +343 -44
- package/src/adapters/rxiv/preprints.test.ts +233 -0
- package/src/adapters/rxiv/preprints.ts +849 -0
- package/src/adapters/scholar-artifacts/pdf-read.ts +277 -0
- package/src/adapters/scholar-artifacts/pdf.ts +133 -0
- package/src/adapters/semantic-scholar/papers.ts +98 -6
- package/src/adapters/unpaywall/works.ts +141 -12
- package/src/adapters/wanfang/search.ts +57 -7
- package/src/adapters/cnki/search.yaml +0 -49
|
@@ -40,8 +40,12 @@ describe("openalex agent-facing commands", () => {
|
|
|
40
40
|
publication_year: 2026,
|
|
41
41
|
cited_by_count: 5,
|
|
42
42
|
authorships: [{ author: { display_name: "Ada" } }],
|
|
43
|
-
primary_location: {
|
|
44
|
-
|
|
43
|
+
primary_location: {
|
|
44
|
+
landing_page_url: "https://publisher.test/paper",
|
|
45
|
+
pdf_url: "https://publisher.test/paper.pdf",
|
|
46
|
+
source: { display_name: "Journal" },
|
|
47
|
+
},
|
|
48
|
+
open_access: { is_oa: true, oa_url: "https://publisher.test/paper" },
|
|
45
49
|
type: "article",
|
|
46
50
|
},
|
|
47
51
|
],
|
|
@@ -62,7 +66,8 @@ describe("openalex agent-facing commands", () => {
|
|
|
62
66
|
is_open_access: true,
|
|
63
67
|
type: "article",
|
|
64
68
|
doi: "10.1/example",
|
|
65
|
-
pdf_url: "",
|
|
69
|
+
pdf_url: "https://publisher.test/paper.pdf",
|
|
70
|
+
landing_url: "https://publisher.test/paper",
|
|
66
71
|
openalex_id: "W1234",
|
|
67
72
|
source_adapter: "openalex",
|
|
68
73
|
source_url: "https://openalex.org/W1234",
|
|
@@ -86,7 +91,11 @@ describe("openalex agent-facing commands", () => {
|
|
|
86
91
|
{ author: { display_name: "Ada" } },
|
|
87
92
|
{ author: { display_name: "Grace" } },
|
|
88
93
|
],
|
|
89
|
-
primary_location: {
|
|
94
|
+
primary_location: {
|
|
95
|
+
landing_page_url: "https://publisher.test/paper",
|
|
96
|
+
source: { display_name: "Journal" },
|
|
97
|
+
},
|
|
98
|
+
best_oa_location: { pdf_url: "https://repository.test/paper.pdf" },
|
|
90
99
|
cited_by_count: 5,
|
|
91
100
|
open_access: { is_oa: true, oa_url: "https://example.test/pdf" },
|
|
92
101
|
referenced_works: ["W1", "W2"],
|
|
@@ -98,6 +107,8 @@ describe("openalex agent-facing commands", () => {
|
|
|
98
107
|
authors: "Ada, Grace",
|
|
99
108
|
referencedCount: 2,
|
|
100
109
|
doi: "10.1/example",
|
|
110
|
+
pdf_url: "https://repository.test/paper.pdf",
|
|
111
|
+
landing_url: "https://publisher.test/paper",
|
|
101
112
|
abstract: "hello world",
|
|
102
113
|
});
|
|
103
114
|
expect(() => mapOpenAlexWorkRow({})).toThrow(
|
|
@@ -1,12 +1,20 @@
|
|
|
1
1
|
/**
|
|
2
|
-
* @owner
|
|
3
|
-
* @does
|
|
4
|
-
* @needs
|
|
5
|
-
* @feeds
|
|
6
|
-
* @breaks
|
|
2
|
+
* @owner src::adapters::openalex::works
|
|
3
|
+
* @does Registers agent-facing OpenAlex work search, detail, and source PDF read commands.
|
|
4
|
+
* @needs Public OpenAlex API, src/adapters/scholar-artifacts/pdf-read.ts, pdftotext
|
|
5
|
+
* @feeds src/commands/scholar.ts via scholar.* capability tags, surface coverage ledger, scholarly work rows
|
|
6
|
+
* @breaks OpenAlex API envelope drift, weak DOI/id parsing, missing OA PDF URLs, or abstract reconstruction errors surface as explicit adapter errors.
|
|
7
|
+
* @invariants Work references normalize to OpenAlex W ids or doi: refs; read requires a source-provided PDF URL before text is claimed.
|
|
8
|
+
* @side-effects HTTPS egress to api.openalex.org and source PDF hosts; read writes one PDF and executes pdftotext.
|
|
9
|
+
* @perf O(limit) JSON mapping for search; O(PDF bytes + extracted page range) for read
|
|
10
|
+
* @concurrency safe
|
|
11
|
+
* @test src/adapters/openalex/works.test.ts, tests/unit/adapters/scholar-sources.test.ts
|
|
12
|
+
* @stability experimental
|
|
13
|
+
* @since 2026-05-19
|
|
7
14
|
*/
|
|
8
15
|
|
|
9
16
|
import { cli, Strategy } from "../../registry.js";
|
|
17
|
+
import { readScholarPdf } from "../scholar-artifacts/pdf-read.js";
|
|
10
18
|
|
|
11
19
|
const OPENALEX_BASE = "https://api.openalex.org";
|
|
12
20
|
const WORK_ID_RE = /^W\d{4,}$/;
|
|
@@ -19,6 +27,7 @@ const SEARCH_SELECT = [
|
|
|
19
27
|
"cited_by_count",
|
|
20
28
|
"authorships",
|
|
21
29
|
"primary_location",
|
|
30
|
+
"best_oa_location",
|
|
22
31
|
"open_access",
|
|
23
32
|
"type",
|
|
24
33
|
].join(",");
|
|
@@ -31,6 +40,7 @@ const WORK_SELECT = [
|
|
|
31
40
|
"cited_by_count",
|
|
32
41
|
"authorships",
|
|
33
42
|
"primary_location",
|
|
43
|
+
"best_oa_location",
|
|
34
44
|
"open_access",
|
|
35
45
|
"type",
|
|
36
46
|
"referenced_works",
|
|
@@ -51,6 +61,15 @@ interface OpenAlexWork {
|
|
|
51
61
|
};
|
|
52
62
|
}>;
|
|
53
63
|
primary_location?: {
|
|
64
|
+
landing_page_url?: unknown;
|
|
65
|
+
pdf_url?: unknown;
|
|
66
|
+
source?: {
|
|
67
|
+
display_name?: unknown;
|
|
68
|
+
};
|
|
69
|
+
};
|
|
70
|
+
best_oa_location?: {
|
|
71
|
+
landing_page_url?: unknown;
|
|
72
|
+
pdf_url?: unknown;
|
|
54
73
|
source?: {
|
|
55
74
|
display_name?: unknown;
|
|
56
75
|
};
|
|
@@ -173,7 +192,25 @@ function authorList(work: OpenAlexWork): string[] {
|
|
|
173
192
|
}
|
|
174
193
|
|
|
175
194
|
function venue(work: OpenAlexWork): string {
|
|
176
|
-
return
|
|
195
|
+
return (
|
|
196
|
+
stringField(work.primary_location?.source?.display_name).trim() ||
|
|
197
|
+
stringField(work.best_oa_location?.source?.display_name).trim()
|
|
198
|
+
);
|
|
199
|
+
}
|
|
200
|
+
|
|
201
|
+
function publisherLandingUrl(work: OpenAlexWork): string {
|
|
202
|
+
return (
|
|
203
|
+
stringField(work.primary_location?.landing_page_url).trim() ||
|
|
204
|
+
stringField(work.best_oa_location?.landing_page_url).trim() ||
|
|
205
|
+
stringField(work.open_access?.oa_url).trim()
|
|
206
|
+
);
|
|
207
|
+
}
|
|
208
|
+
|
|
209
|
+
function openAlexPdfUrl(work: OpenAlexWork): string {
|
|
210
|
+
return (
|
|
211
|
+
stringField(work.primary_location?.pdf_url).trim() ||
|
|
212
|
+
stringField(work.best_oa_location?.pdf_url).trim()
|
|
213
|
+
);
|
|
177
214
|
}
|
|
178
215
|
|
|
179
216
|
export function mapOpenAlexSearchRows(
|
|
@@ -195,7 +232,8 @@ export function mapOpenAlexSearchRows(
|
|
|
195
232
|
is_open_access: Boolean(work.open_access?.is_oa),
|
|
196
233
|
type: stringField(work.type).trim(),
|
|
197
234
|
doi: bareDoi(work.doi),
|
|
198
|
-
pdf_url:
|
|
235
|
+
pdf_url: openAlexPdfUrl(work),
|
|
236
|
+
landing_url: publisherLandingUrl(work) || undefined,
|
|
199
237
|
openalex_id: id,
|
|
200
238
|
source_adapter: "openalex",
|
|
201
239
|
source_url: id ? `https://openalex.org/${id}` : "",
|
|
@@ -225,7 +263,8 @@ export function mapOpenAlexWorkRow(
|
|
|
225
263
|
openAccess: Boolean(work.open_access?.is_oa),
|
|
226
264
|
is_open_access: Boolean(work.open_access?.is_oa),
|
|
227
265
|
openAccessUrl: stringField(work.open_access?.oa_url).trim(),
|
|
228
|
-
pdf_url:
|
|
266
|
+
pdf_url: openAlexPdfUrl(work),
|
|
267
|
+
landing_url: publisherLandingUrl(work) || undefined,
|
|
229
268
|
referencedCount: Array.isArray(work.referenced_works)
|
|
230
269
|
? work.referenced_works.length
|
|
231
270
|
: null,
|
|
@@ -242,6 +281,33 @@ export function mapOpenAlexWorkRow(
|
|
|
242
281
|
};
|
|
243
282
|
}
|
|
244
283
|
|
|
284
|
+
async function readOpenAlexWorkPdf(
|
|
285
|
+
row: Record<string, unknown>,
|
|
286
|
+
kwargs: Record<string, unknown>,
|
|
287
|
+
): Promise<Record<string, unknown>> {
|
|
288
|
+
const pdfUrl = stringField(row.pdf_url);
|
|
289
|
+
if (!pdfUrl) {
|
|
290
|
+
const id = stringField(row.id) || stringField(row.openalex_id) || "record";
|
|
291
|
+
throw new Error(`OpenAlex work ${id} has no source PDF URL.`);
|
|
292
|
+
}
|
|
293
|
+
return readScholarPdf(
|
|
294
|
+
{
|
|
295
|
+
...kwargs,
|
|
296
|
+
id: stringField(row.id) || stringField(row.openalex_id) || pdfUrl,
|
|
297
|
+
title: stringField(row.title) || pdfUrl,
|
|
298
|
+
source_adapter: "openalex",
|
|
299
|
+
source_url: stringField(row.source_url) || stringField(row.url),
|
|
300
|
+
pdf_url: pdfUrl,
|
|
301
|
+
},
|
|
302
|
+
{
|
|
303
|
+
site: "openalex",
|
|
304
|
+
command: "read",
|
|
305
|
+
defaultOutput: "./openalex-downloads",
|
|
306
|
+
userAgent: "unicli-openalex/1.0 (https://github.com/olo-dot-io/Uni-CLI)",
|
|
307
|
+
},
|
|
308
|
+
);
|
|
309
|
+
}
|
|
310
|
+
|
|
245
311
|
async function fetchOpenAlex(url: string, label: string): Promise<unknown> {
|
|
246
312
|
const response = await fetch(appendMailto(url), {
|
|
247
313
|
headers: {
|
|
@@ -350,3 +416,65 @@ cli({
|
|
|
350
416
|
return [mapOpenAlexWorkRow(work)];
|
|
351
417
|
},
|
|
352
418
|
});
|
|
419
|
+
|
|
420
|
+
cli({
|
|
421
|
+
site: "openalex",
|
|
422
|
+
name: "read",
|
|
423
|
+
description: "Download an OpenAlex open-access Work PDF and extract text",
|
|
424
|
+
domain: "api.openalex.org",
|
|
425
|
+
strategy: Strategy.PUBLIC,
|
|
426
|
+
args: [
|
|
427
|
+
{
|
|
428
|
+
name: "id",
|
|
429
|
+
type: "str",
|
|
430
|
+
required: true,
|
|
431
|
+
positional: true,
|
|
432
|
+
description: "OpenAlex Work id or DOI",
|
|
433
|
+
},
|
|
434
|
+
{
|
|
435
|
+
name: "output",
|
|
436
|
+
type: "str",
|
|
437
|
+
default: "./openalex-downloads",
|
|
438
|
+
description: "Output directory for the downloaded PDF",
|
|
439
|
+
"x-unicli-kind": "path",
|
|
440
|
+
},
|
|
441
|
+
{ name: "filename", type: "str", description: "Output PDF filename" },
|
|
442
|
+
{ name: "first-page", type: "int", default: 1, description: "First page" },
|
|
443
|
+
{ name: "last-page", type: "int", default: 20, description: "Last page" },
|
|
444
|
+
{
|
|
445
|
+
name: "max-chars",
|
|
446
|
+
type: "int",
|
|
447
|
+
default: 40000,
|
|
448
|
+
description: "Maximum extracted text characters",
|
|
449
|
+
},
|
|
450
|
+
],
|
|
451
|
+
columns: [
|
|
452
|
+
"id",
|
|
453
|
+
"title",
|
|
454
|
+
"source_adapter",
|
|
455
|
+
"source_url",
|
|
456
|
+
"pdf_url",
|
|
457
|
+
"path",
|
|
458
|
+
"text_source",
|
|
459
|
+
"text",
|
|
460
|
+
"text_chars",
|
|
461
|
+
"text_truncated",
|
|
462
|
+
],
|
|
463
|
+
capabilities: [
|
|
464
|
+
"http.fetch",
|
|
465
|
+
"http.download",
|
|
466
|
+
"subprocess.exec",
|
|
467
|
+
"scholar.fulltext",
|
|
468
|
+
"scholar.pdf",
|
|
469
|
+
],
|
|
470
|
+
executables: ["pdftotext"],
|
|
471
|
+
minimum_capability: "subprocess.exec",
|
|
472
|
+
func: async (_page, kwargs) => {
|
|
473
|
+
const ref = requireOpenAlexWorkRef(kwargs.id);
|
|
474
|
+
const work = (await fetchOpenAlex(
|
|
475
|
+
`${OPENALEX_BASE}/works/${encodeURIComponent(ref)}?select=${WORK_SELECT}`,
|
|
476
|
+
"openalex work",
|
|
477
|
+
)) as OpenAlexWork;
|
|
478
|
+
return [await readOpenAlexWorkPdf(mapOpenAlexWorkRow(work), kwargs)];
|
|
479
|
+
},
|
|
480
|
+
});
|
|
@@ -7,10 +7,13 @@ import {
|
|
|
7
7
|
formatOpenReviewDate,
|
|
8
8
|
mapOpenReviewNoteRow,
|
|
9
9
|
mapReviewThreadRows,
|
|
10
|
+
openReviewPdfFilename,
|
|
10
11
|
readContent,
|
|
11
12
|
requireForumId,
|
|
13
|
+
requireOpenReviewMaxChars,
|
|
12
14
|
requireOpenReviewLimit,
|
|
13
15
|
requireOpenReviewOffset,
|
|
16
|
+
requireOpenReviewPageRange,
|
|
14
17
|
requireProfileId,
|
|
15
18
|
} from "./papers.js";
|
|
16
19
|
|
|
@@ -26,11 +29,25 @@ describe("openreview agent-facing paper commands", () => {
|
|
|
26
29
|
expect(requireOpenReviewOffset(undefined)).toBe(0);
|
|
27
30
|
expect(() => requireOpenReviewOffset("-1")).toThrow("non-negative");
|
|
28
31
|
expect(requireForumId("5sRnsubyAK")).toBe("5sRnsubyAK");
|
|
32
|
+
expect(requireForumId("https://openreview.net/forum?id=5sRnsubyAK")).toBe(
|
|
33
|
+
"5sRnsubyAK",
|
|
34
|
+
);
|
|
29
35
|
expect(() => requireForumId("https://openreview.net/forum?id=x")).toThrow(
|
|
30
36
|
"not a valid",
|
|
31
37
|
);
|
|
32
38
|
expect(requireProfileId("~Yoshua_Bengio1")).toBe("~Yoshua_Bengio1");
|
|
33
39
|
expect(() => requireProfileId("Yoshua_Bengio1")).toThrow("not valid");
|
|
40
|
+
expect(requireOpenReviewPageRange("2", "4")).toEqual({
|
|
41
|
+
firstPage: 2,
|
|
42
|
+
lastPage: 4,
|
|
43
|
+
});
|
|
44
|
+
expect(() => requireOpenReviewPageRange("4", "2")).toThrow("last-page");
|
|
45
|
+
expect(requireOpenReviewMaxChars(undefined)).toBe(40000);
|
|
46
|
+
expect(requireOpenReviewMaxChars("1000")).toBe(1000);
|
|
47
|
+
expect(() => requireOpenReviewMaxChars("999")).toThrow("max-chars");
|
|
48
|
+
expect(openReviewPdfFilename("abcDEF123", "A / Paper: Demo")).toBe(
|
|
49
|
+
"abcDEF123-A-Paper-Demo.pdf",
|
|
50
|
+
);
|
|
34
51
|
});
|
|
35
52
|
|
|
36
53
|
it("maps OpenReview content.value note fields", () => {
|
|
@@ -64,7 +81,14 @@ describe("openreview agent-facing paper commands", () => {
|
|
|
64
81
|
abstract: "Long abstract",
|
|
65
82
|
pdate: "2025-10-09",
|
|
66
83
|
pdf: "https://openreview.net/pdf/abc.pdf",
|
|
84
|
+
pdf_url: "https://openreview.net/pdf/abc.pdf",
|
|
67
85
|
url: "https://openreview.net/forum?id=5sRnsubyAK",
|
|
86
|
+
source_url: "https://openreview.net/forum?id=5sRnsubyAK",
|
|
87
|
+
landing_url: "https://openreview.net/forum?id=5sRnsubyAK",
|
|
88
|
+
source_adapter: "openreview",
|
|
89
|
+
openreview_id: "5sRnsubyAK",
|
|
90
|
+
date: "2025-10-09",
|
|
91
|
+
retrieved_at: expect.any(String),
|
|
68
92
|
});
|
|
69
93
|
});
|
|
70
94
|
|
|
@@ -129,9 +153,16 @@ describe("openreview agent-facing paper commands", () => {
|
|
|
129
153
|
"DECISION",
|
|
130
154
|
]);
|
|
131
155
|
expect(rows[1]).toMatchObject({
|
|
156
|
+
forum: "forum123",
|
|
157
|
+
note_id: "early",
|
|
132
158
|
author: "Reviewer_abc",
|
|
159
|
+
invitation: "Venue/-/Official_Review",
|
|
160
|
+
created_at: "1970-01-01",
|
|
161
|
+
source_url: "https://openreview.net/forum?id=forum123¬eId=early",
|
|
133
162
|
rating: "8: accept",
|
|
134
163
|
confidence: "4: high",
|
|
164
|
+
text_chars: expect.any(Number),
|
|
165
|
+
text_truncated: true,
|
|
135
166
|
});
|
|
136
167
|
expect(String(rows[1].text)).toHaveLength(200);
|
|
137
168
|
expect(String(rows[1].text).endsWith("...")).toBe(true);
|