@yeyuan98/opencode-bioresearcher-plugin 1.2.0 → 1.2.2

package/dist/parser-tools/pubmed/pubmed.d.ts

@@ -7,6 +7,7 @@ export declare const parse_pubmed_articleSet: {
         outputMode: z.ZodDefault<z.ZodEnum<{
             single: "single";
             individual: "individual";
+            excel: "excel";
         }>>;
         outputFileName: z.ZodOptional<z.ZodString>;
         outputDir: z.ZodOptional<z.ZodString>;
@@ -14,7 +15,7 @@ export declare const parse_pubmed_articleSet: {
     };
     execute(args: {
         filePath: string;
-        outputMode: "single" | "individual";
+        outputMode: "single" | "individual" | "excel";
         verbose: boolean;
         outputFileName?: string | undefined;
         outputDir?: string | undefined;

package/dist/parser-tools/pubmed/pubmed.js

@@ -4,7 +4,7 @@ import { readFileSync, writeFileSync, mkdirSync, existsSync } from 'fs';
 import { gunzipSync } from 'zlib';
 import { join, resolve } from 'path';
 import { z } from 'zod';
-import { toArray, extractAllFields, generateArticleMarkdown } from './utils.js';
+import { toArray, extractAllFields, generateArticleMarkdown, generateExcelFile } from './utils.js';
 function formatError(error) {
     const message = error instanceof Error ? error.message : String(error);
     return JSON.stringify({ error: message }, null, 2);
@@ -114,7 +114,18 @@ function processArticles(articleXmls, outputPath, mode, outputFileName, verbose
         }
     }
     ensureDir(outputPath);
-    if (mode === 'single') {
+    if (mode === 'excel') {
+        const fileName = outputFileName || 'pubmed_articles.xlsx';
+        const filePath = join(outputPath, fileName);
+        generateExcelFile(parsedArticles, filePath);
+        if (verbose)
+            console.log(`Wrote Excel file: ${filePath}`);
+        return {
+            filePath,
+            stats: { total: articleXmls.length, successful: successCount, failed: failCount }
+        };
+    }
+    else if (mode === 'single') {
         const fileName = outputFileName || 'pubmed_articles.md';
         const filePath = join(outputPath, fileName);
         const allMarkdown = parsedArticles
@@ -145,13 +156,13 @@ function processArticles(articleXmls, outputPath, mode, outputFileName, verbose
     }
 }
 export const parse_pubmed_articleSet = tool({
-    description: 'Parse PubMed XML file and convert to markdown format. Supports both .xml and .xml.gz files. Can output all articles in a single file or as individual markdown files.',
+    description: 'Parse PubMed XML file and convert to markdown or Excel format. Supports both .xml and .xml.gz files. Output modes: single markdown file, individual markdown files, or single Excel file.',
     args: {
         filePath: z.string()
             .describe('Path to XML PubMed file (.xml or .xml.gz)'),
-        outputMode: z.enum(['single', 'individual'])
+        outputMode: z.enum(['single', 'individual', 'excel'])
             .default('single')
-            .describe('Output mode: single file or individual files per article'),
+            .describe('Output mode: single markdown file, individual markdown files, or single Excel file'),
         outputFileName: z.string()
             .optional()
             .describe('Custom output file/directory name (default: pubmed_articles)'),

package/dist/parser-tools/pubmed/types.d.ts

@@ -93,7 +93,6 @@ export interface ParsedArticle {
     doi: string | null;
     abstract: string | null;
     keywords: string[];
-    publicationDate?: string;
     error?: string;
 }
 export interface ProcessingStats {
@@ -101,3 +100,13 @@ export interface ProcessingStats {
     successful: number;
     failed: number;
 }
+export interface ExcelRow {
+    PMID: string;
+    Title: string;
+    Authors: string;
+    Journal: string;
+    DOI: string;
+    Abstract: string;
+    Keywords: string;
+    Error: string;
+}

package/dist/parser-tools/pubmed/utils.d.ts

@@ -8,6 +8,6 @@ export declare function extractJournalInfo(article: PubmedArticle): string;
 export declare function extractDOI(article: PubmedArticle): string | null;
 export declare function extractAbstract(article: PubmedArticle): string | null;
 export declare function extractKeywords(article: PubmedArticle): string[];
-export declare function extractPublicationDate(article: PubmedArticle): string | undefined;
 export declare function extractAllFields(article: PubmedArticle): ParsedArticle;
 export declare function generateArticleMarkdown(data: ParsedArticle): string;
+export declare function generateExcelFile(articles: ParsedArticle[], outputFilePath: string): void;

package/dist/parser-tools/pubmed/utils.js

@@ -1,3 +1,4 @@
+import XLSX from 'xlsx';
 export function getText(obj) {
     if (obj === null || obj === undefined)
         return null;
@@ -52,7 +53,6 @@ export function extractJournalInfo(article) {
     const year = getText(pubDate?.Year) || '';
     const volume = getText(journalIssue?.Volume) || '';
     const issue = getText(journalIssue?.Issue) || '';
-    const pages = getText(article.MedlineCitation?.Article?.Pagination?.MedlinePgn) || '';
     let info = title;
     if (year)
         info += `, ${year}`;
@@ -63,8 +63,6 @@ export function extractJournalInfo(article) {
         if (issue)
             info += `(${issue})`;
     }
-    if (pages)
-        info += `:${pages}`;
     return info;
 }
 export function extractDOI(article) {
@@ -97,26 +95,6 @@ export function extractKeywords(article) {
         .map(kw => getText(kw))
         .filter((kw) => kw !== null && kw.length > 0);
 }
-export function extractPublicationDate(article) {
-    const history = article.PubmedData?.History;
-    if (!history)
-        return undefined;
-    const pubDates = toArray(history.PubMedPubDate);
-    const pubDate = pubDates.find(p => p['@_PubStatus'] === 'pubmed' || p['@_PubStatus'] === 'medline');
-    if (!pubDate)
-        return undefined;
-    const year = getText(pubDate.Year) || '';
-    const month = getText(pubDate.Month) || '';
-    const day = getText(pubDate.Day) || '';
-    let date;
-    if (year)
-        date = year;
-    if (month)
-        date = `${date || ''} ${month}`;
-    if (day)
-        date = `${date || ''} ${day}`;
-    return date || undefined;
-}
 export function extractAllFields(article) {
     return {
         PMID: extractPMID(article),
@@ -125,8 +103,7 @@ export function extractAllFields(article) {
         journal: extractJournalInfo(article),
         doi: extractDOI(article),
         abstract: extractAbstract(article),
-        keywords: extractKeywords(article),
-        publicationDate: extractPublicationDate(article)
+        keywords: extractKeywords(article)
     };
 }
 export function generateArticleMarkdown(data) {
@@ -136,9 +113,6 @@ export function generateArticleMarkdown(data) {
     }
     markdown += `## PMID\n${data.PMID}\n\n`;
     markdown += `## Title\n${data.title}\n\n`;
-    if (data.publicationDate) {
-        markdown += `## Publication Date\n${data.publicationDate}\n\n`;
-    }
     markdown += `## Authors\n`;
     data.authors.forEach(author => {
         markdown += `- ${author}\n`;
@@ -156,3 +130,19 @@ export function generateArticleMarkdown(data) {
     }
     return markdown;
 }
+export function generateExcelFile(articles, outputFilePath) {
+    const excelRows = articles.map(article => ({
+        PMID: article.error ? `[ERROR] ${article.PMID}` : article.PMID,
+        Title: article.title,
+        Authors: article.authors.join(', '),
+        Journal: article.journal,
+        DOI: article.doi || '',
+        Abstract: article.abstract || '',
+        Keywords: article.keywords.join(', '),
+        Error: article.error || ''
+    }));
+    const workbook = XLSX.utils.book_new();
+    const worksheet = XLSX.utils.json_to_sheet(excelRows);
+    XLSX.utils.book_append_sheet(workbook, worksheet, 'PubMed Articles');
+    XLSX.writeFile(workbook, outputFilePath);
+}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@yeyuan98/opencode-bioresearcher-plugin",
-  "version": "1.2.0",
+  "version": "1.2.2",
   "description": "OpenCode plugin that adds a bioresearcher agent",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",