arXiv support

.gitignore

@@ -1 +1,4 @@
-build
+build
+.gitignore
+.DS_Store
+*.xpi

src/bootstrap.js

@@ -16,6 +16,7 @@ async function startup({ id, version, rootURI }) {
     Services.scriptloader.loadSubScript(rootURI + 'chrome/content/threadpool.js');
     Services.scriptloader.loadSubScript(rootURI + 'chrome/content/journal.js');
     Services.scriptloader.loadSubScript(rootURI + 'chrome/content/book.js');
+    Services.scriptloader.loadSubScript(rootURI + 'chrome/content/arxiv.js');
     Services.scriptloader.loadSubScript(rootURI + 'chrome/content/zotmeta.js');
     ZotMeta.init({ id, version, rootURI });
     ZotMeta.addToAllWindows();

src/chrome/content/arxiv.js

@@ -0,0 +1,87 @@
+Arxiv = {    
+    generateAuthors(authors) {
+        var newAuthorList = [];
+        if (authors) {
+            authors.forEach(author => {
+                newAuthorList.push(
+                    {
+                        "firstName": author["given"] || "",
+                        "lastName": author["family"] || "",
+                        "creatorType": "author"
+                    }
+                );
+            });
+        }
+        return newAuthorList;
+    },
+
+    generateDate(date) {
+        if (!date) {
+            return null;
+        }
+        return date.split("T")[0]; // 提取日期部分 (YYYY-MM-DD 格式)
+    },
+
+    getMetaData(item) {
+        var arxivID = item.getField('archiveID').split(":")[1];
+        if (!arxivID) {
+            return null; // ArXiv ID 是必需的
+        }
+
+        var url = `https://export.arxiv.org/api/query?id_list=${arxivID}`;
+        return Utilities.fetchWithTimeout(url, { method: 'GET' }, 3000)
+            .then(response => {
+                if (!response.ok) {
+                    Utilities.publishError("Error retrieving metadata", 
+                        "Please check if the ArXiv ID is correct and if you have network access to arxiv.org.");
+                    return null;
+                }
+                return response.text();
+            })
+            .then(data => {
+                try {
+                    // 解析 ArXiv API 返回的 XML 数据
+                    let parser = new DOMParser();
+                    let xmlDoc = parser.parseFromString(data, "application/xml");
+
+                    let title = xmlDoc.querySelector("entry > title")?.textContent.trim();
+                    let authors = Array.from(xmlDoc.querySelectorAll("entry > author")).map(author => ({
+                        given: author.querySelector("name").textContent.split(" ").slice(0, -1).join(" "),
+                        family: author.querySelector("name").textContent.split(" ").slice(-1).join(" ")
+                    }));
+                    let published = xmlDoc.querySelector("entry > published")?.textContent.trim();
+                    let summary = xmlDoc.querySelector("entry > summary")?.textContent.trim();
+                    let journalRef = xmlDoc.querySelector("entry > arxiv\\:journal_ref")?.textContent.trim();
+                    let doi = xmlDoc.querySelector("entry > arxiv\\:doi")?.textContent.trim();
+
+                    return {
+                        "Title": title || "",
+                        "Authors": this.generateAuthors(authors),
+                        "PublishDate": this.generateDate(published),
+                        "Abstract": summary || "",
+                        "JournalRef": journalRef || "",
+                        "DOI": doi || ""
+                    };
+                } catch (error) {
+                    Utilities.publishError("Error parsing metadata", "Unable to parse metadata from ArXiv.");
+                    return null;
+                }
+            });
+    },
+
+    async updateMetadata(item) {
+        var metaData = await this.getMetaData(item);
+        if (!metaData) {
+            return 1;
+        }
+
+        if (!Utilities.isEmpty(metaData["Title"]))       item.setField('title', metaData["Title"]);
+        if (!Utilities.isEmpty(metaData["Authors"]))     item.setCreators(metaData["Authors"]);
+        if (!Utilities.isEmpty(metaData["PublishDate"])) item.setField('date', metaData["PublishDate"]);
+        if (!Utilities.isEmpty(metaData["Abstract"]))    item.setField('abstractNote', metaData["Abstract"]);
+        if (!Utilities.isEmpty(metaData["JournalRef"]))  item.setField('publicationTitle', metaData["JournalRef"]);
+        if (!Utilities.isEmpty(metaData["DOI"]))         item.setField('DOI', metaData["DOI"]);
+        await item.saveTx();
+        return 0;
+    }
+};

src/chrome/content/overlay.xul

@@ -6,6 +6,7 @@
     <script src="threadpool.js"/>
     <script src="utilities.js"/>
     <script src="journal.js"/>
+    <script src="arxiv.js"/>
     <script src="book.js"/>
     <script src="zotmeta.js"/>
 </overlay>

src/chrome/content/zotmeta.js

@@ -102,6 +102,8 @@ ZotMeta = {
                     status = await Book.updateMetadata(item);
                 } else if (item.itemTypeID === Zotero.ItemTypes.getID('journalArticle')) {
                     status = await Journal.updateMetadata(item);
+                } else if (item.itemTypeID === Zotero.ItemTypes.getID('preprint') && item.repository == 'arXiv') {
+                    status = await Arxiv.updateMetadata(item);
                 } else {
                     status = 1;
                 }