Bringing Crossref, Semantic Scholar, Open Citations and Open Alex lookup + auto-import to Cita for Zotero 7

package.json

@@ -36,6 +36,7 @@
 	},
 	"homepage": "https://github.com/diegodlh/zotero-cita",
 	"dependencies": {
+		"openalex-sdk": "^1.1.6",
 		"prop-types": "^15.7.2",
 		"quickstatements-to-wikibase-edit": "^1.2.1",
 		"react": "^18.3.1",
@@ -46,6 +47,7 @@
 	},
 	"devDependencies": {
 		"@types/language-tags": "^1.0.4",
+		"@types/lodash": "^4.17.9",
 		"@types/node": "^20.10.4",
 		"@types/react-dom": "^18.3.0",
 		"eslint": "^8.55.0",

patches/openalex-sdk+1.1.6.patch

@@ -0,0 +1,91 @@
+diff --git a/node_modules/openalex-sdk/dist/src/index.js b/node_modules/openalex-sdk/dist/src/index.js
+index 70b2df5..518d455 100644
+--- a/node_modules/openalex-sdk/dist/src/index.js
++++ b/node_modules/openalex-sdk/dist/src/index.js
+@@ -3,7 +3,7 @@ var __importDefault = (this && this.__importDefault) || function (mod) {
+     return (mod && mod.__esModule) ? mod : { "default": mod };
+ };
+ Object.defineProperty(exports, "__esModule", { value: true });
+-const fs_1 = __importDefault(require("fs"));
++//const fs_1 = __importDefault(require("fs"));
+ const authors_1 = require("./utils/authors");
+ const exportCSV_1 = require("./utils/exportCSV");
+ const helpers_1 = require("./utils/helpers");
+diff --git a/node_modules/openalex-sdk/dist/src/utils/authors.js b/node_modules/openalex-sdk/dist/src/utils/authors.js
+index 0b1cbc5..f824766 100644
+--- a/node_modules/openalex-sdk/dist/src/utils/authors.js
++++ b/node_modules/openalex-sdk/dist/src/utils/authors.js
+@@ -4,7 +4,7 @@ var __importDefault = (this && this.__importDefault) || function (mod) {
+ };
+ Object.defineProperty(exports, "__esModule", { value: true });
+ exports.handleAllAuthorsPages = exports.handleMultipleAuthorsPages = exports.validateAuthorParameters = void 0;
+-const fs_1 = __importDefault(require("fs"));
++//const fs_1 = __importDefault(require("fs"));
+ const exportCSV_1 = require("./exportCSV");
+ const helpers_1 = require("./helpers");
+ const http_1 = require("./http");
+diff --git a/node_modules/openalex-sdk/dist/src/utils/exportCSV.js b/node_modules/openalex-sdk/dist/src/utils/exportCSV.js
+index 7f4d748..9c01df5 100644
+--- a/node_modules/openalex-sdk/dist/src/utils/exportCSV.js
++++ b/node_modules/openalex-sdk/dist/src/utils/exportCSV.js
+@@ -4,7 +4,7 @@ var __importDefault = (this && this.__importDefault) || function (mod) {
+ };
+ Object.defineProperty(exports, "__esModule", { value: true });
+ exports.convertToCSV = void 0;
+-const fs_1 = __importDefault(require("fs"));
++//const fs_1 = __importDefault(require("fs"));
+ function flattenObject(obj, parentKey = '', depth = 0) {
+     const flattened = {};
+     for (const [key, value] of Object.entries(obj)) {
+diff --git a/node_modules/openalex-sdk/dist/src/utils/institutions.js b/node_modules/openalex-sdk/dist/src/utils/institutions.js
+index 1082435..099275a 100644
+--- a/node_modules/openalex-sdk/dist/src/utils/institutions.js
++++ b/node_modules/openalex-sdk/dist/src/utils/institutions.js
+@@ -4,7 +4,7 @@ var __importDefault = (this && this.__importDefault) || function (mod) {
+ };
+ Object.defineProperty(exports, "__esModule", { value: true });
+ exports.handleAllInstitutionsPages = exports.handleMultipleInstitutionsPages = exports.validateInstitutionsParameters = void 0;
+-const fs_1 = __importDefault(require("fs"));
++//const fs_1 = __importDefault(require("fs"));
+ const exportCSV_1 = require("./exportCSV");
+ const helpers_1 = require("./helpers");
+ const http_1 = require("./http");
+diff --git a/node_modules/openalex-sdk/dist/src/utils/sources.js b/node_modules/openalex-sdk/dist/src/utils/sources.js
+index 699da8d..38c68b8 100644
+--- a/node_modules/openalex-sdk/dist/src/utils/sources.js
++++ b/node_modules/openalex-sdk/dist/src/utils/sources.js
+@@ -4,7 +4,7 @@ var __importDefault = (this && this.__importDefault) || function (mod) {
+ };
+ Object.defineProperty(exports, "__esModule", { value: true });
+ exports.handleAllSourcesPages = exports.handleMultipleSourcesPages = exports.validateSourcesParameters = void 0;
+-const fs_1 = __importDefault(require("fs"));
++//const fs_1 = __importDefault(require("fs"));
+ const exportCSV_1 = require("./exportCSV");
+ const helpers_1 = require("./helpers");
+ const http_1 = require("./http");
+diff --git a/node_modules/openalex-sdk/dist/src/utils/topics.js b/node_modules/openalex-sdk/dist/src/utils/topics.js
+index b2946cc..b9fd0ed 100644
+--- a/node_modules/openalex-sdk/dist/src/utils/topics.js
++++ b/node_modules/openalex-sdk/dist/src/utils/topics.js
+@@ -4,7 +4,7 @@ var __importDefault = (this && this.__importDefault) || function (mod) {
+ };
+ Object.defineProperty(exports, "__esModule", { value: true });
+ exports.handleAllTopicsPages = exports.handleMultipleTopicsPages = exports.validateTopicsParameters = void 0;
+-const fs_1 = __importDefault(require("fs"));
++//const fs_1 = __importDefault(require("fs"));
+ const exportCSV_1 = require("./exportCSV");
+ const helpers_1 = require("./helpers");
+ const http_1 = require("./http");
+diff --git a/node_modules/openalex-sdk/dist/src/utils/works.js b/node_modules/openalex-sdk/dist/src/utils/works.js
+index 46d5d38..2a5591c 100644
+--- a/node_modules/openalex-sdk/dist/src/utils/works.js
++++ b/node_modules/openalex-sdk/dist/src/utils/works.js
+@@ -4,7 +4,7 @@ var __importDefault = (this && this.__importDefault) || function (mod) {
+ };
+ Object.defineProperty(exports, "__esModule", { value: true });
+ exports.formatNumber = exports.handleAllPagesInChunks = exports.handleMultiplePages = exports.handleAllPages = exports.validateParameters = void 0;
+-const fs_1 = __importDefault(require("fs"));
++//const fs_1 = __importDefault(require("fs"));
+ const exportCSV_1 = require("./exportCSV");
+ const helpers_1 = require("./helpers");
+ const http_1 = require("./http");

src/cita/citation.ts

@@ -15,7 +15,7 @@ class Citation {
 	ocis: {
 		citingId: string;
 		citedId: string;
-		idType: "qid" | "doi" | "occ";
+		idType: "qid" | "doi" | "omid";
 		oci: string;
 		supplierName: string;
 		valid: boolean;
@@ -330,7 +330,7 @@ class Citation {
 			return;
 		}
 
-		if (item.libraryID !== this.source.item.libraryID) {
+		if (item.libraryID && item.libraryID !== this.source.item.libraryID) {
 			Services.prompt.alert(
 				window as mozIDOMWindowProxy,
 				"",

src/cita/crossref.ts

@@ -1,17 +1,229 @@
-/* eslint-disable @typescript-eslint/no-unsafe-member-access */
-/* eslint-disable @typescript-eslint/no-unsafe-call */
-import Wikicite from "./wikicite";
-
-declare const Services: any;
-
-export default class Crossref {
-	static getCitations() {
-		Services.prompt.alert(
-			window,
-			Wikicite.getString("wikicite.global.unsupported"),
-			Wikicite.getString("wikicite.crossref.get-citations.unsupported"),
+import { IndexerBase, IndexedWork, LookupIdentifier } from "./indexer";
+import ItemWrapper from "./itemWrapper";
+import Wikicite, { debug } from "./wikicite";
+import Lookup from "./zotLookup";
+
+interface CrossrefResponse {
+	status: string;
+	"message-type": string;
+	"message-version": string;
+	message: CrossrefWork;
+}
+
+interface CrossrefWork {
+	"reference-count": number;
+	reference: Reference[];
+	"references-count": number;
+}
+
+interface Reference {
+	key: string;
+	issn?: string;
+	"standards-body"?: string;
+	"series-title"?: string;
+	"isbn-type"?: string;
+	"doi-asserted-by"?: string;
+	DOI?: string;
+	ISBN?: string;
+	component?: string;
+	"article-title"?: string;
+	"volume-title"?: string;
+	author?: string;
+	year?: string;
+	unstructured?: string;
+	issue?: string;
+	"first-page"?: string;
+	volume?: string;
+	"journal-title"?: string;
+	edition?: string;
+	"standard-designator"?: string;
+	"issn-type"?: string;
+}
+
+function mapCrossrefWorkToIndexedWork(
+	work: CrossrefWork,
+): IndexedWork<Reference> {
+	return {
+		referenceCount: work["reference-count"], // Map Crossref's `reference-count` to `IndexedWork`'s `referenceCount`
+		referencedWorks: work.reference, // Map `reference` to `referencedWorks`
+	};
+}
+
+export default class Crossref extends IndexerBase<Reference> {
+	indexerName = "Crossref";
+
+	supportedPIDs: PIDType[] = ["DOI"];
+
+	async fetchDOI(item: ItemWrapper): Promise<string | null> {
+		const crossrefOpenURL =
+			"https://doi.crossref.org/[email protected]&";
+		const ctx = Zotero.OpenURL.createContextObject(item, "1.0");
+
+		if (ctx) {
+			const url = crossrefOpenURL + ctx + "&multihit=true";
+			const response = await Zotero.HTTP.request("GET", url).catch(
+				(e) => {
+					debug(
+						`Couldn't access URL: ${url}. Got status ${e.status}.`,
+					);
+				},
+			);
+
+			const xml = response?.responseXML;
+
+			if (xml) {
+				const status = xml
+					.getElementsByTagName("query")[0]
+					.getAttribute("status");
+				switch (status) {
+					case "resolved":
+					case "multiresolved": {
+						// We just take the first one
+						const doi =
+							xml.getElementsByTagName("doi")[0].textContent;
+						return doi;
+					}
+					case "unresolved":
+						return null;
+					default:
+						throw new Error(`Unexpected status: ${status}`);
+				}
+			}
+		}
+		return null;
+	}
+
+	/**
+	 * Get a list of references from Crossref for an item with a certain DOI.
+	 * Returned in JSON Crossref format.
+	 * @param {string[]} identifiers - DOI for the item for which to get references.
+	 * @returns {Promise<IndexedWork<Reference>[]>} list of references, or [] if none.
+	 */
+	async getReferences(
+		identifiers: LookupIdentifier[],
+	): Promise<IndexedWork<Reference>[]> {
+		// Crossref-specific logic for fetching references
+		const requests = identifiers.map(async (doi) => {
+			const url = `https://api.crossref.org/works/${Zotero.Utilities.cleanDOI(doi.id)}`;
+			const options = {
+				headers: {
+					"User-Agent": `${Wikicite.getUserAgent()} mailto:[email protected]`,
+				},
+				responseType: "json",
+			};
+			const response = await Zotero.HTTP.request(
+				"GET",
+				url,
+				options,
+			).catch((e) => {
+				debug(`Couldn't access URL: ${url}. Got status ${e.status}.`);
+				if (e.status == 429) {
+					// Extract rate limit headers
+					const rateLimitLimit =
+						e.xmlhttp.getResponseHeader("X-Rate-Limit-Limit");
+					const rateLimitInterval = e.xmlhttp.getResponseHeader(
+						"X-Rate-Limit-Interval",
+					);
+
+					throw new Error(
+						"Received a 429 rate limit response from Crossref (https://github.com/CrossRef/rest-api-doc#rate-limits). Try getting references for fewer items at a time. Rate limits in action: Limit: ${rateLimitLimit}, Interval: ${rateLimitInterval}",
+					);
+				}
+			});
+
+			const crossrefWork = (response?.response as CrossrefResponse)
+				.message;
+			return mapCrossrefWorkToIndexedWork(crossrefWork); // Map to IndexedWork<Reference>
+		});
+		return Promise.all(requests);
+	}
+
+	/**
+	 * Parse a list of references in JSON Crossref format.
+	 * @param {Reference[]} references - Array of Crossref references to parse to Zotero items.
+	 * @returns {Promise<Zotero.Item[]>} Zotero items parsed from references (where parsing is possible).
+	 */
+	async parseReferences(references: Reference[]): Promise<Zotero.Item[]> {
+		// Crossref-specific parsing logic
+		// Extract one identifier per reference (prioritising DOI) and filter out those without identifiers
+		const _identifiers = references
+			.map((ref) => ref.DOI ?? ref.ISBN ?? null)
+			.filter((e) => e !== null);
+		// Remove duplicates and extract identifiers
+		const identifiers = [...new Set(_identifiers)].flatMap((e) =>
+			Zotero.Utilities.extractIdentifiers(e!),
+		);
+		const crossrefReferencesWithoutIdentifier = references.filter(
+			(item) => !item.DOI && !item.ISBN,
 		);
+
+		// Use Lookup to get items for all identifiers
+		const result = await Lookup.lookupItemsByIdentifiers(identifiers);
+		const parsedReferences = result ? result : [];
+
+		// Manually create items for references without identifiers
+		const manualResult = await Promise.allSettled(
+			crossrefReferencesWithoutIdentifier.map((item) =>
+				this.parseItemFromCrossrefReference(item),
+			),
+		);
+		const parsedReferencesWithoutIdentifier = manualResult
+			.filter(
+				(ref): ref is PromiseFulfilledResult<Zotero.Item> =>
+					ref.status === "fulfilled",
+			) // Only keep fulfilled promises
+			.map((ref) => ref.value); // Extract the `value` from fulfilled promises;
+		parsedReferences.push(...parsedReferencesWithoutIdentifier);
+
+		return parsedReferences;
 	}
 
-	static getDOI() {}
+	/**
+	 * Create a Zotero Item from a Crossref reference item that doesn't include an identifier.
+	 * @param {Reference} crossrefItem - A reference item in JSON Crossref format.
+	 * @returns {Promise<Zotero.Item>} Zotero item parsed from the identifier, or null if parsing failed.
+	 */
+	async parseItemFromCrossrefReference(
+		crossrefItem: Reference,
+	): Promise<Zotero.Item> {
+		//Zotero.log(`Parsing ${crossrefItem.unstructured}`);
+		const jsonItem: any = {};
+		if (crossrefItem["journal-title"]) {
+			jsonItem.itemType = "journalArticle";
+			jsonItem.title =
+				crossrefItem["article-title"] || crossrefItem["volume-title"];
+			jsonItem.publicationTitle = crossrefItem["journal-title"];
+		} else if (crossrefItem["volume-title"]) {
+			jsonItem.itemType = "book";
+			jsonItem.title = crossrefItem["volume-title"];
+		} else if (crossrefItem.unstructured) {
+			// todo: Implement reference text parsing here
+			throw new Error(
+				"Couldn't parse Crossref reference - unstructured references are not yet supported. " +
+					JSON.stringify(crossrefItem),
+			);
+		} else {
+			throw new Error(
+				"Couldn't determine type of Crossref reference - doesn't contain `journal-title` or `volume-title` field. " +
+					JSON.stringify(crossrefItem),
+			);
+		}
+		jsonItem.date = crossrefItem.year;
+		jsonItem.pages = crossrefItem["first-page"];
+		jsonItem.volume = crossrefItem.volume;
+		jsonItem.issue = crossrefItem.issue;
+		jsonItem.creators = crossrefItem.author
+			? [Zotero.Utilities.cleanAuthor(crossrefItem.author, "author")]
+			: [];
+		// remove undefined properties
+		for (const key in jsonItem) {
+			if (jsonItem[key] === undefined) {
+				delete jsonItem[key];
+			}
+		}
+
+		const newItem = new Zotero.Item(jsonItem.itemType);
+		newItem.fromJSON(jsonItem);
+		return newItem;
+	}
 }

src/cita/extract.ts

@@ -1,13 +1,9 @@
-/* eslint-disable @typescript-eslint/no-unsafe-member-access */
-/* eslint-disable @typescript-eslint/no-unsafe-call */
 import Wikicite from "./wikicite";
 
-declare const Services: any;
-
 export default class Extraction {
 	static extract() {
 		Services.prompt.alert(
-			window,
+			window as mozIDOMWindowProxy,
 			Wikicite.getString("wikicite.global.unsupported"),
 			Wikicite.getString("wikicite.extract.unsupported"),
 		);