@ncukondo/search-hub 0.12.1 → 0.12.2

package/dist/fulltext/download/downloader.d.ts

@@ -1,21 +0,0 @@
-/**
- * PDF downloader with retry and error handling.
- */
-export interface DownloadOptions {
-    /** Number of retry attempts (default: 3) */
-    retries?: number;
-    /** Base delay between retries in ms (default: 1000) */
-    retryDelay?: number;
-}
-export interface DownloadResult {
-    success: boolean;
-    size?: number;
-    error?: string;
-}
-/**
- * Download a PDF from a URL to a local file path.
- * Retries on network errors and 429 responses with exponential backoff.
- * Does not retry on 403/404 or other client errors.
- */
-export declare function downloadPdf(url: string, destPath: string, options?: DownloadOptions): Promise<DownloadResult>;
-//# sourceMappingURL=downloader.d.ts.map

package/dist/fulltext/download/downloader.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"downloader.d.ts","sourceRoot":"","sources":["../../../src/fulltext/download/downloader.ts"],"names":[],"mappings":"AAAA;;GAEG;AAKH,MAAM,WAAW,eAAe;IAC9B,4CAA4C;IAC5C,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,uDAAuD;IACvD,UAAU,CAAC,EAAE,MAAM,CAAC;CACrB;AAED,MAAM,WAAW,cAAc;IAC7B,OAAO,EAAE,OAAO,CAAC;IACjB,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,KAAK,CAAC,EAAE,MAAM,CAAC;CAChB;AAoBD;;;;GAIG;AACH,wBAAsB,WAAW,CAC/B,GAAG,EAAE,MAAM,EACX,QAAQ,EAAE,MAAM,EAChB,OAAO,CAAC,EAAE,eAAe,GACxB,OAAO,CAAC,cAAc,CAAC,CAoDzB"}

package/dist/fulltext/download/downloader.js

@@ -1,59 +0,0 @@
-import { mkdir, writeFile } from "node:fs/promises";
-import { dirname } from "node:path";
-const NON_RETRYABLE_STATUSES = /* @__PURE__ */ new Set([400, 401, 403, 404, 405, 410]);
-const VALID_CONTENT_TYPES = ["application/pdf", "application/octet-stream"];
-const USER_AGENT = "search-hub/0.8.0 (https://github.com/ncukondo/search-hub)";
-function isValidPdfContentType(contentType) {
-  if (!contentType) return false;
-  const base = (contentType.split(";")[0] ?? "").trim().toLowerCase();
-  return VALID_CONTENT_TYPES.includes(base);
-}
-function sleep(ms) {
-  return new Promise((resolve) => setTimeout(resolve, ms));
-}
-async function downloadPdf(url, destPath, options) {
-  const retries = options?.retries ?? 3;
-  const retryDelay = options?.retryDelay ?? 1e3;
-  let lastError;
-  for (let attempt = 1; attempt <= retries; attempt++) {
-    try {
-      const response = await fetch(url, {
-        headers: { "User-Agent": USER_AGENT }
-      });
-      if (!response.ok) {
-        const status = response.status;
-        if (NON_RETRYABLE_STATUSES.has(status)) {
-          return { success: false, error: `HTTP ${status} ${response.statusText}` };
-        }
-        lastError = `HTTP ${status} ${response.statusText}`;
-        if (attempt < retries) {
-          await sleep(retryDelay * attempt);
-          continue;
-        }
-        return { success: false, error: lastError };
-      }
-      const contentType = response.headers.get("content-type");
-      if (!isValidPdfContentType(contentType)) {
-        return {
-          success: false,
-          error: `Unexpected Content-Type: ${contentType ?? "none"}`
-        };
-      }
-      const buffer = await response.arrayBuffer();
-      await mkdir(dirname(destPath), { recursive: true });
-      await writeFile(destPath, Buffer.from(buffer));
-      return { success: true, size: buffer.byteLength };
-    } catch (err) {
-      lastError = err instanceof Error ? err.message : String(err);
-      if (attempt < retries) {
-        await sleep(retryDelay * attempt);
-        continue;
-      }
-    }
-  }
-  return { success: false, error: lastError ?? "Download failed" };
-}
-export {
-  downloadPdf
-};
-//# sourceMappingURL=downloader.js.map

package/dist/fulltext/download/downloader.js.map

@@ -1 +0,0 @@
-{"version":3,"file":"downloader.js","sources":["../../../src/fulltext/download/downloader.ts"],"sourcesContent":["/**\n * PDF downloader with retry and error handling.\n */\n\nimport { writeFile, mkdir } from 'node:fs/promises';\nimport { dirname } from 'node:path';\n\nexport interface DownloadOptions {\n  /** Number of retry attempts (default: 3) */\n  retries?: number;\n  /** Base delay between retries in ms (default: 1000) */\n  retryDelay?: number;\n}\n\nexport interface DownloadResult {\n  success: boolean;\n  size?: number;\n  error?: string;\n}\n\n/** HTTP status codes that should not be retried */\nconst NON_RETRYABLE_STATUSES = new Set([400, 401, 403, 404, 405, 410]);\n\n/** Content types accepted as valid PDF responses */\nconst VALID_CONTENT_TYPES = ['application/pdf', 'application/octet-stream'];\n\nconst USER_AGENT = 'search-hub/0.8.0 (https://github.com/ncukondo/search-hub)';\n\nfunction isValidPdfContentType(contentType: string | null): boolean {\n  if (!contentType) return false;\n  const base = (contentType.split(';')[0] ?? '').trim().toLowerCase();\n  return VALID_CONTENT_TYPES.includes(base);\n}\n\nfunction sleep(ms: number): Promise<void> {\n  return new Promise((resolve) => setTimeout(resolve, ms));\n}\n\n/**\n * Download a PDF from a URL to a local file path.\n * Retries on network errors and 429 responses with exponential backoff.\n * Does not retry on 403/404 or other client errors.\n */\nexport async function downloadPdf(\n  url: string,\n  destPath: string,\n  options?: DownloadOptions,\n): Promise<DownloadResult> {\n  const retries = options?.retries ?? 3;\n  const retryDelay = options?.retryDelay ?? 1000;\n\n  let lastError: string | undefined;\n\n  for (let attempt = 1; attempt <= retries; attempt++) {\n    try {\n      const response = await fetch(url, {\n        headers: { 'User-Agent': USER_AGENT },\n      });\n\n      if (!response.ok) {\n        const status = response.status;\n        if (NON_RETRYABLE_STATUSES.has(status)) {\n          return { success: false, error: `HTTP ${status} ${response.statusText}` };\n        }\n        // Retryable status (429, 5xx)\n        lastError = `HTTP ${status} ${response.statusText}`;\n        if (attempt < retries) {\n          await sleep(retryDelay * attempt);\n          continue;\n        }\n        return { success: false, error: lastError };\n      }\n\n      // Validate content type\n      const contentType = response.headers.get('content-type');\n      if (!isValidPdfContentType(contentType)) {\n        return {\n          success: false,\n          error: `Unexpected Content-Type: ${contentType ?? 'none'}`,\n        };\n      }\n\n      const buffer = await response.arrayBuffer();\n\n      // Ensure parent directory exists\n      await mkdir(dirname(destPath), { recursive: true });\n      await writeFile(destPath, Buffer.from(buffer));\n\n      return { success: true, size: buffer.byteLength };\n    } catch (err) {\n      lastError = err instanceof Error ? err.message : String(err);\n      if (attempt < retries) {\n        await sleep(retryDelay * attempt);\n        continue;\n      }\n    }\n  }\n\n  return { success: false, error: lastError ?? 'Download failed' };\n}\n"],"names":[],"mappings":";;AAqBA,MAAM,yBAAyB,oBAAI,IAAI,CAAC,KAAK,KAAK,KAAK,KAAK,KAAK,GAAG,CAAC;AAGrE,MAAM,sBAAsB,CAAC,mBAAmB,0BAA0B;AAE1E,MAAM,aAAa;AAEnB,SAAS,sBAAsB,aAAqC;AAClE,MAAI,CAAC,YAAa,QAAO;AACzB,QAAM,QAAQ,YAAY,MAAM,GAAG,EAAE,CAAC,KAAK,IAAI,KAAA,EAAO,YAAA;AACtD,SAAO,oBAAoB,SAAS,IAAI;AAC1C;AAEA,SAAS,MAAM,IAA2B;AACxC,SAAO,IAAI,QAAQ,CAAC,YAAY,WAAW,SAAS,EAAE,CAAC;AACzD;AAOA,eAAsB,YACpB,KACA,UACA,SACyB;AACzB,QAAM,UAAU,SAAS,WAAW;AACpC,QAAM,aAAa,SAAS,cAAc;AAE1C,MAAI;AAEJ,WAAS,UAAU,GAAG,WAAW,SAAS,WAAW;AACnD,QAAI;AACF,YAAM,WAAW,MAAM,MAAM,KAAK;AAAA,QAChC,SAAS,EAAE,cAAc,WAAA;AAAA,MAAW,CACrC;AAED,UAAI,CAAC,SAAS,IAAI;AAChB,cAAM,SAAS,SAAS;AACxB,YAAI,uBAAuB,IAAI,MAAM,GAAG;AACtC,iBAAO,EAAE,SAAS,OAAO,OAAO,QAAQ,MAAM,IAAI,SAAS,UAAU,GAAA;AAAA,QACvE;AAEA,oBAAY,QAAQ,MAAM,IAAI,SAAS,UAAU;AACjD,YAAI,UAAU,SAAS;AACrB,gBAAM,MAAM,aAAa,OAAO;AAChC;AAAA,QACF;AACA,eAAO,EAAE,SAAS,OAAO,OAAO,UAAA;AAAA,MAClC;AAGA,YAAM,cAAc,SAAS,QAAQ,IAAI,cAAc;AACvD,UAAI,CAAC,sBAAsB,WAAW,GAAG;AACvC,eAAO;AAAA,UACL,SAAS;AAAA,UACT,OAAO,4BAA4B,eAAe,MAAM;AAAA,QAAA;AAAA,MAE5D;AAEA,YAAM,SAAS,MAAM,SAAS,YAAA;AAG9B,YAAM,MAAM,QAAQ,QAAQ,GAAG,EAAE,WAAW,MAAM;AAClD,YAAM,UAAU,UAAU,OAAO,KAAK,MAAM,CAAC;AAE7C,aAAO,EAAE,SAAS,MAAM,MAAM,OAAO,WAAA;AAAA,IACvC,SAAS,KAAK;AACZ,kBAAY,eAAe,QAAQ,IAAI,UAAU,OAAO,GAAG;AAC3D,UAAI,UAAU,SAAS;AACrB,cAAM,MAAM,aAAa,OAAO;AAChC;AAAA,MACF;AAAA,IACF;AAAA,EACF;AAEA,SAAO,EAAE,SAAS,OAAO,OAAO,aAAa,kBAAA;AAC/C;"}

package/dist/fulltext/download/orchestrator.d.ts

@@ -1,33 +0,0 @@
-import { OALocation } from '../types';
-export interface FetchArticle {
-    dirName: string;
-    oaLocations: OALocation[];
-    pmcid?: string;
-}
-export interface FetchOptions {
-    concurrency?: number;
-    retries?: number;
-    retryDelay?: number;
-    onProgress?: (progress: {
-        completed: number;
-        total: number;
-        dirName: string;
-    }) => void;
-    sourceFilter?: string[];
-}
-export interface FetchResult {
-    dirName: string;
-    status: 'downloaded' | 'failed' | 'skipped';
-    filesDownloaded?: string[];
-    error?: string;
-}
-/**
- * Fetch fulltext for a single article.
- * Downloads PDF from the best available source, plus PMC XML if available.
- */
-export declare function fetchFulltext(article: FetchArticle, sessionDir: string, options?: FetchOptions): Promise<FetchResult>;
-/**
- * Fetch fulltexts for multiple articles with concurrency control.
- */
-export declare function fetchAllFulltexts(articles: FetchArticle[], sessionDir: string, options?: FetchOptions): Promise<FetchResult[]>;
-//# sourceMappingURL=orchestrator.d.ts.map

package/dist/fulltext/download/orchestrator.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"orchestrator.d.ts","sourceRoot":"","sources":["../../../src/fulltext/download/orchestrator.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAIH,OAAO,KAAK,EAAE,UAAU,EAA0B,MAAM,UAAU,CAAC;AASnE,MAAM,WAAW,YAAY;IAC3B,OAAO,EAAE,MAAM,CAAC;IAChB,WAAW,EAAE,UAAU,EAAE,CAAC;IAC1B,KAAK,CAAC,EAAE,MAAM,CAAC;CAChB;AAED,MAAM,WAAW,YAAY;IAC3B,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB,UAAU,CAAC,EAAE,CAAC,QAAQ,EAAE;QAAE,SAAS,EAAE,MAAM,CAAC;QAAC,KAAK,EAAE,MAAM,CAAC;QAAC,OAAO,EAAE,MAAM,CAAA;KAAE,KAAK,IAAI,CAAC;IACvF,YAAY,CAAC,EAAE,MAAM,EAAE,CAAC;CACzB;AAED,MAAM,WAAW,WAAW;IAC1B,OAAO,EAAE,MAAM,CAAC;IAChB,MAAM,EAAE,YAAY,GAAG,QAAQ,GAAG,SAAS,CAAC;IAC5C,eAAe,CAAC,EAAE,MAAM,EAAE,CAAC;IAC3B,KAAK,CAAC,EAAE,MAAM,CAAC;CAChB;AAgBD;;;GAGG;AACH,wBAAsB,aAAa,CACjC,OAAO,EAAE,YAAY,EACrB,UAAU,EAAE,MAAM,EAClB,OAAO,CAAC,EAAE,YAAY,GACrB,OAAO,CAAC,WAAW,CAAC,CA4FtB;AAED;;GAEG;AACH,wBAAsB,iBAAiB,CACrC,QAAQ,EAAE,YAAY,EAAE,EACxB,UAAU,EAAE,MAAM,EAClB,OAAO,CAAC,EAAE,YAAY,GACrB,OAAO,CAAC,WAAW,EAAE,CAAC,CAgCxB"}

package/dist/fulltext/download/orchestrator.js

@@ -1,125 +0,0 @@
-import { mkdir } from "node:fs/promises";
-import { join } from "node:path";
-import { downloadPdf } from "./downloader.js";
-import { downloadPmcXml } from "./pmc-xml.js";
-import { loadMeta, saveMeta } from "../meta.js";
-import { getArticleDir } from "../paths.js";
-const SOURCE_PRIORITY = ["pmc", "arxiv", "unpaywall", "core", "publisher"];
-function sortByPriority(locations) {
-  return [...locations].sort((a, b) => {
-    const aIdx = SOURCE_PRIORITY.indexOf(a.source);
-    const bIdx = SOURCE_PRIORITY.indexOf(b.source);
-    return (aIdx === -1 ? 999 : aIdx) - (bIdx === -1 ? 999 : bIdx);
-  });
-}
-function getPdfLocations(locations) {
-  return locations.filter((loc) => loc.urlType === "pdf");
-}
-async function fetchFulltext(article, sessionDir, options) {
-  const articleDir = getArticleDir(sessionDir, article.dirName);
-  const metaPath = join(articleDir, "meta.json");
-  let meta;
-  try {
-    meta = await loadMeta(metaPath);
-  } catch {
-    return { dirName: article.dirName, status: "failed", error: "meta.json not found" };
-  }
-  if (meta.files.pdf) {
-    return { dirName: article.dirName, status: "skipped" };
-  }
-  await mkdir(articleDir, { recursive: true });
-  const filesDownloaded = [];
-  let pdfFileInfo;
-  let xmlFileInfo;
-  let locations = article.oaLocations;
-  if (options?.sourceFilter && options.sourceFilter.length > 0) {
-    locations = locations.filter((loc) => options.sourceFilter?.includes(loc.source));
-  }
-  const pdfLocations = sortByPriority(getPdfLocations(locations));
-  for (const loc of pdfLocations) {
-    const pdfPath = join(articleDir, "fulltext.pdf");
-    const downloadResult = await downloadPdf(loc.url, pdfPath, {
-      retries: options?.retries ?? 3,
-      retryDelay: options?.retryDelay ?? 1e3
-    });
-    if (downloadResult.success) {
-      filesDownloaded.push("fulltext.pdf");
-      const info = {
-        filename: "fulltext.pdf",
-        source: loc.source,
-        retrievedAt: (/* @__PURE__ */ new Date()).toISOString()
-      };
-      if (downloadResult.size !== void 0) info.size = downloadResult.size;
-      pdfFileInfo = info;
-      break;
-    }
-  }
-  if (article.pmcid) {
-    const xmlPath = join(articleDir, "fulltext.xml");
-    const xmlResult = await downloadPmcXml(article.pmcid, xmlPath);
-    if (xmlResult.success) {
-      filesDownloaded.push("fulltext.xml");
-      const info = {
-        filename: "fulltext.xml",
-        source: "pmc",
-        retrievedAt: (/* @__PURE__ */ new Date()).toISOString()
-      };
-      if (xmlResult.size !== void 0) info.size = xmlResult.size;
-      xmlFileInfo = info;
-    }
-  }
-  if (filesDownloaded.length === 0) {
-    return {
-      dirName: article.dirName,
-      status: "failed",
-      error: "All download sources failed"
-    };
-  }
-  const updatedMeta = {
-    ...meta,
-    files: {
-      ...meta.files,
-      ...pdfFileInfo ? { pdf: pdfFileInfo } : {},
-      ...xmlFileInfo ? { xml: xmlFileInfo } : {}
-    }
-  };
-  await saveMeta(metaPath, updatedMeta);
-  return {
-    dirName: article.dirName,
-    status: "downloaded",
-    filesDownloaded
-  };
-}
-async function fetchAllFulltexts(articles, sessionDir, options) {
-  const concurrency = options?.concurrency ?? 3;
-  const results = new Array(articles.length);
-  let nextIndex = 0;
-  let completed = 0;
-  async function worker() {
-    while (nextIndex < articles.length) {
-      const index = nextIndex++;
-      const article = articles[index];
-      if (!article) continue;
-      results[index] = await fetchFulltext(article, sessionDir, options);
-      completed++;
-      if (options?.onProgress) {
-        options.onProgress({
-          completed,
-          total: articles.length,
-          dirName: article.dirName
-        });
-      }
-    }
-  }
-  const workers = Array.from(
-    { length: Math.min(concurrency, articles.length) },
-    () => worker()
-  );
-  await Promise.all(workers);
-  return results;
-}
-export {
-  fetchAllFulltexts,
-  fetchFulltext
-};
-//# sourceMappingURL=orchestrator.js.map

package/dist/fulltext/download/orchestrator.js.map

@@ -1 +0,0 @@
-{"version":3,"file":"orchestrator.js","sources":["../../../src/fulltext/download/orchestrator.ts"],"sourcesContent":["/**\n * Fulltext fetch orchestrator.\n * Coordinates downloads from multiple OA sources with priority-based selection.\n */\n\nimport { mkdir } from 'node:fs/promises';\nimport { join } from 'node:path';\nimport type { OALocation, FulltextMeta, FileInfo } from '../types';\nimport { downloadPdf } from './downloader';\nimport { downloadPmcXml } from './pmc-xml';\nimport { loadMeta, saveMeta } from '../meta';\nimport { getArticleDir } from '../paths';\n\n/** Source priority order (lower index = higher priority) */\nconst SOURCE_PRIORITY: string[] = ['pmc', 'arxiv', 'unpaywall', 'core', 'publisher'];\n\nexport interface FetchArticle {\n  dirName: string;\n  oaLocations: OALocation[];\n  pmcid?: string;\n}\n\nexport interface FetchOptions {\n  concurrency?: number;\n  retries?: number;\n  retryDelay?: number;\n  onProgress?: (progress: { completed: number; total: number; dirName: string }) => void;\n  sourceFilter?: string[];\n}\n\nexport interface FetchResult {\n  dirName: string;\n  status: 'downloaded' | 'failed' | 'skipped';\n  filesDownloaded?: string[];\n  error?: string;\n}\n\n/** Sort OA locations by source priority */\nfunction sortByPriority(locations: OALocation[]): OALocation[] {\n  return [...locations].sort((a, b) => {\n    const aIdx = SOURCE_PRIORITY.indexOf(a.source);\n    const bIdx = SOURCE_PRIORITY.indexOf(b.source);\n    return (aIdx === -1 ? 999 : aIdx) - (bIdx === -1 ? 999 : bIdx);\n  });\n}\n\n/** Get only PDF-type locations */\nfunction getPdfLocations(locations: OALocation[]): OALocation[] {\n  return locations.filter((loc) => loc.urlType === 'pdf');\n}\n\n/**\n * Fetch fulltext for a single article.\n * Downloads PDF from the best available source, plus PMC XML if available.\n */\nexport async function fetchFulltext(\n  article: FetchArticle,\n  sessionDir: string,\n  options?: FetchOptions,\n): Promise<FetchResult> {\n  const articleDir = getArticleDir(sessionDir, article.dirName);\n  const metaPath = join(articleDir, 'meta.json');\n\n  // Load meta to check existing files\n  let meta: FulltextMeta;\n  try {\n    meta = await loadMeta(metaPath);\n  } catch {\n    return { dirName: article.dirName, status: 'failed', error: 'meta.json not found' };\n  }\n\n  // Skip if already has PDF\n  if (meta.files.pdf) {\n    return { dirName: article.dirName, status: 'skipped' };\n  }\n\n  // Ensure directory exists\n  await mkdir(articleDir, { recursive: true });\n\n  const filesDownloaded: string[] = [];\n  let pdfFileInfo: FileInfo | undefined;\n  let xmlFileInfo: FileInfo | undefined;\n\n  // Filter and sort locations by priority\n  let locations = article.oaLocations;\n  if (options?.sourceFilter && options.sourceFilter.length > 0) {\n    locations = locations.filter((loc) => options.sourceFilter?.includes(loc.source));\n  }\n  const pdfLocations = sortByPriority(getPdfLocations(locations));\n\n  // Try downloading PDF from best source, falling back to next on failure\n  for (const loc of pdfLocations) {\n    const pdfPath = join(articleDir, 'fulltext.pdf');\n    const downloadResult = await downloadPdf(loc.url, pdfPath, {\n      retries: options?.retries ?? 3,\n      retryDelay: options?.retryDelay ?? 1000,\n    });\n\n    if (downloadResult.success) {\n      filesDownloaded.push('fulltext.pdf');\n      const info: FileInfo = {\n        filename: 'fulltext.pdf',\n        source: loc.source,\n        retrievedAt: new Date().toISOString(),\n      };\n      if (downloadResult.size !== undefined) info.size = downloadResult.size;\n      pdfFileInfo = info;\n      break;\n    }\n  }\n\n  // Download PMC XML if pmcid available\n  if (article.pmcid) {\n    const xmlPath = join(articleDir, 'fulltext.xml');\n    const xmlResult = await downloadPmcXml(article.pmcid, xmlPath);\n    if (xmlResult.success) {\n      filesDownloaded.push('fulltext.xml');\n      const info: FileInfo = {\n        filename: 'fulltext.xml',\n        source: 'pmc',\n        retrievedAt: new Date().toISOString(),\n      };\n      if (xmlResult.size !== undefined) info.size = xmlResult.size;\n      xmlFileInfo = info;\n    }\n  }\n\n  if (filesDownloaded.length === 0) {\n    return {\n      dirName: article.dirName,\n      status: 'failed',\n      error: 'All download sources failed',\n    };\n  }\n\n  // Update meta.json with new file info\n  const updatedMeta: FulltextMeta = {\n    ...meta,\n    files: {\n      ...meta.files,\n      ...(pdfFileInfo ? { pdf: pdfFileInfo } : {}),\n      ...(xmlFileInfo ? { xml: xmlFileInfo } : {}),\n    },\n  };\n  await saveMeta(metaPath, updatedMeta);\n\n  return {\n    dirName: article.dirName,\n    status: 'downloaded',\n    filesDownloaded,\n  };\n}\n\n/**\n * Fetch fulltexts for multiple articles with concurrency control.\n */\nexport async function fetchAllFulltexts(\n  articles: FetchArticle[],\n  sessionDir: string,\n  options?: FetchOptions,\n): Promise<FetchResult[]> {\n  const concurrency = options?.concurrency ?? 3;\n  const results: FetchResult[] = new Array(articles.length);\n  let nextIndex = 0;\n  let completed = 0;\n\n  async function worker(): Promise<void> {\n    while (nextIndex < articles.length) {\n      const index = nextIndex++;\n      const article = articles[index];\n      if (!article) continue;\n\n      results[index] = await fetchFulltext(article, sessionDir, options);\n      completed++;\n\n      if (options?.onProgress) {\n        options.onProgress({\n          completed,\n          total: articles.length,\n          dirName: article.dirName,\n        });\n      }\n    }\n  }\n\n  const workers = Array.from(\n    { length: Math.min(concurrency, articles.length) },\n    () => worker(),\n  );\n  await Promise.all(workers);\n\n  return results;\n}\n"],"names":[],"mappings":";;;;;;AAcA,MAAM,kBAA4B,CAAC,OAAO,SAAS,aAAa,QAAQ,WAAW;AAwBnF,SAAS,eAAe,WAAuC;AAC7D,SAAO,CAAC,GAAG,SAAS,EAAE,KAAK,CAAC,GAAG,MAAM;AACnC,UAAM,OAAO,gBAAgB,QAAQ,EAAE,MAAM;AAC7C,UAAM,OAAO,gBAAgB,QAAQ,EAAE,MAAM;AAC7C,YAAQ,SAAS,KAAK,MAAM,SAAS,SAAS,KAAK,MAAM;AAAA,EAC3D,CAAC;AACH;AAGA,SAAS,gBAAgB,WAAuC;AAC9D,SAAO,UAAU,OAAO,CAAC,QAAQ,IAAI,YAAY,KAAK;AACxD;AAMA,eAAsB,cACpB,SACA,YACA,SACsB;AACtB,QAAM,aAAa,cAAc,YAAY,QAAQ,OAAO;AAC5D,QAAM,WAAW,KAAK,YAAY,WAAW;AAG7C,MAAI;AACJ,MAAI;AACF,WAAO,MAAM,SAAS,QAAQ;AAAA,EAChC,QAAQ;AACN,WAAO,EAAE,SAAS,QAAQ,SAAS,QAAQ,UAAU,OAAO,sBAAA;AAAA,EAC9D;AAGA,MAAI,KAAK,MAAM,KAAK;AAClB,WAAO,EAAE,SAAS,QAAQ,SAAS,QAAQ,UAAA;AAAA,EAC7C;AAGA,QAAM,MAAM,YAAY,EAAE,WAAW,MAAM;AAE3C,QAAM,kBAA4B,CAAA;AAClC,MAAI;AACJ,MAAI;AAGJ,MAAI,YAAY,QAAQ;AACxB,MAAI,SAAS,gBAAgB,QAAQ,aAAa,SAAS,GAAG;AAC5D,gBAAY,UAAU,OAAO,CAAC,QAAQ,QAAQ,cAAc,SAAS,IAAI,MAAM,CAAC;AAAA,EAClF;AACA,QAAM,eAAe,eAAe,gBAAgB,SAAS,CAAC;AAG9D,aAAW,OAAO,cAAc;AAC9B,UAAM,UAAU,KAAK,YAAY,cAAc;AAC/C,UAAM,iBAAiB,MAAM,YAAY,IAAI,KAAK,SAAS;AAAA,MACzD,SAAS,SAAS,WAAW;AAAA,MAC7B,YAAY,SAAS,cAAc;AAAA,IAAA,CACpC;AAED,QAAI,eAAe,SAAS;AAC1B,sBAAgB,KAAK,cAAc;AACnC,YAAM,OAAiB;AAAA,QACrB,UAAU;AAAA,QACV,QAAQ,IAAI;AAAA,QACZ,cAAa,oBAAI,KAAA,GAAO,YAAA;AAAA,MAAY;AAEtC,UAAI,eAAe,SAAS,OAAW,MAAK,OAAO,eAAe;AAClE,oBAAc;AACd;AAAA,IACF;AAAA,EACF;AAGA,MAAI,QAAQ,OAAO;AACjB,UAAM,UAAU,KAAK,YAAY,cAAc;AAC/C,UAAM,YAAY,MAAM,eAAe,QAAQ,OAAO,OAAO;AAC7D,QAAI,UAAU,SAAS;AACrB,sBAAgB,KAAK,cAAc;AACnC,YAAM,OAAiB;AAAA,QACrB,UAAU;AAAA,QACV,QAAQ;AAAA,QACR,cAAa,oBAAI,KAAA,GAAO,YAAA;AAAA,MAAY;AAEtC,UAAI,UAAU,SAAS,OAAW,MAAK,OAAO,UAAU;AACxD,oBAAc;AAAA,IAChB;AAAA,EACF;AAEA,MAAI,gBAAgB,WAAW,GAAG;AAChC,WAAO;AAAA,MACL,SAAS,QAAQ;AAAA,MACjB,QAAQ;AAAA,MACR,OAAO;AAAA,IAAA;AAAA,EAEX;AAGA,QAAM,cAA4B;AAAA,IAChC,GAAG;AAAA,IACH,OAAO;AAAA,MACL,GAAG,KAAK;AAAA,MACR,GAAI,cAAc,EAAE,KAAK,YAAA,IAAgB,CAAA;AAAA,MACzC,GAAI,cAAc,EAAE,KAAK,gBAAgB,CAAA;AAAA,IAAC;AAAA,EAC5C;AAEF,QAAM,SAAS,UAAU,WAAW;AAEpC,SAAO;AAAA,IACL,SAAS,QAAQ;AAAA,IACjB,QAAQ;AAAA,IACR;AAAA,EAAA;AAEJ;AAKA,eAAsB,kBACpB,UACA,YACA,SACwB;AACxB,QAAM,cAAc,SAAS,eAAe;AAC5C,QAAM,UAAyB,IAAI,MAAM,SAAS,MAAM;AACxD,MAAI,YAAY;AAChB,MAAI,YAAY;AAEhB,iBAAe,SAAwB;AACrC,WAAO,YAAY,SAAS,QAAQ;AAClC,YAAM,QAAQ;AACd,YAAM,UAAU,SAAS,KAAK;AAC9B,UAAI,CAAC,QAAS;AAEd,cAAQ,KAAK,IAAI,MAAM,cAAc,SAAS,YAAY,OAAO;AACjE;AAEA,UAAI,SAAS,YAAY;AACvB,gBAAQ,WAAW;AAAA,UACjB;AAAA,UACA,OAAO,SAAS;AAAA,UAChB,SAAS,QAAQ;AAAA,QAAA,CAClB;AAAA,MACH;AAAA,IACF;AAAA,EACF;AAEA,QAAM,UAAU,MAAM;AAAA,IACpB,EAAE,QAAQ,KAAK,IAAI,aAAa,SAAS,MAAM,EAAA;AAAA,IAC/C,MAAM,OAAA;AAAA,EAAO;AAEf,QAAM,QAAQ,IAAI,OAAO;AAEzB,SAAO;AACT;"}

package/dist/fulltext/download/pmc-xml.d.ts

@@ -1,13 +0,0 @@
-/**
- * PMC XML downloader via E-utilities.
- */
-export interface PmcXmlResult {
-    success: boolean;
-    size?: number;
-    error?: string;
-}
-/**
- * Download PMC XML for a given PMCID via E-utilities efetch.
- */
-export declare function downloadPmcXml(pmcid: string, destPath: string): Promise<PmcXmlResult>;
-//# sourceMappingURL=pmc-xml.d.ts.map

package/dist/fulltext/download/pmc-xml.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"pmc-xml.d.ts","sourceRoot":"","sources":["../../../src/fulltext/download/pmc-xml.ts"],"names":[],"mappings":"AAAA;;GAEG;AAuBH,MAAM,WAAW,YAAY;IAC3B,OAAO,EAAE,OAAO,CAAC;IACjB,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,KAAK,CAAC,EAAE,MAAM,CAAC;CAChB;AAED;;GAEG;AACH,wBAAsB,cAAc,CAClC,KAAK,EAAE,MAAM,EACb,QAAQ,EAAE,MAAM,GACf,OAAO,CAAC,YAAY,CAAC,CAoCvB"}

package/dist/fulltext/download/pmc-xml.js.map

@@ -1 +0,0 @@
-{"version":3,"file":"pmc-xml.js","sources":["../../../src/fulltext/download/pmc-xml.ts"],"sourcesContent":["/**\n * PMC XML downloader via E-utilities.\n */\n\nimport { writeFile, mkdir } from 'node:fs/promises';\nimport { dirname } from 'node:path';\n\nconst PMC_EFETCH_URL = 'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi';\n\n/** Content types accepted as valid XML responses */\nconst VALID_XML_TYPES = ['text/xml', 'application/xml'];\n\nconst USER_AGENT = 'search-hub/0.8.0 (https://github.com/ncukondo/search-hub)';\n\nfunction isValidXmlContentType(contentType: string | null): boolean {\n  if (!contentType) return false;\n  const base = (contentType.split(';')[0] ?? '').trim().toLowerCase();\n  return VALID_XML_TYPES.includes(base);\n}\n\n/** Strip \"PMC\" prefix if present, returning numeric ID */\nfunction normalizePmcid(pmcid: string): string {\n  return pmcid.replace(/^PMC/i, '');\n}\n\nexport interface PmcXmlResult {\n  success: boolean;\n  size?: number;\n  error?: string;\n}\n\n/**\n * Download PMC XML for a given PMCID via E-utilities efetch.\n */\nexport async function downloadPmcXml(\n  pmcid: string,\n  destPath: string,\n): Promise<PmcXmlResult> {\n  const numericId = normalizePmcid(pmcid);\n  const url = `${PMC_EFETCH_URL}?db=pmc&id=${numericId}&rettype=xml`;\n\n  try {\n    const response = await fetch(url, {\n      headers: { 'User-Agent': USER_AGENT },\n    });\n\n    if (!response.ok) {\n      return {\n        success: false,\n        error: `HTTP ${response.status} ${response.statusText}`,\n      };\n    }\n\n    const contentType = response.headers.get('content-type');\n    if (!isValidXmlContentType(contentType)) {\n      return {\n        success: false,\n        error: `Unexpected Content-Type: ${contentType ?? 'none'} (expected XML)`,\n      };\n    }\n\n    const text = await response.text();\n\n    await mkdir(dirname(destPath), { recursive: true });\n    await writeFile(destPath, text, 'utf-8');\n\n    return { success: true, size: Buffer.byteLength(text) };\n  } catch (err) {\n    return {\n      success: false,\n      error: err instanceof Error ? err.message : String(err),\n    };\n  }\n}\n"],"names":[],"mappings":";;AAOA,MAAM,iBAAiB;AAGvB,MAAM,kBAAkB,CAAC,YAAY,iBAAiB;AAEtD,MAAM,aAAa;AAEnB,SAAS,sBAAsB,aAAqC;AAClE,MAAI,CAAC,YAAa,QAAO;AACzB,QAAM,QAAQ,YAAY,MAAM,GAAG,EAAE,CAAC,KAAK,IAAI,KAAA,EAAO,YAAA;AACtD,SAAO,gBAAgB,SAAS,IAAI;AACtC;AAGA,SAAS,eAAe,OAAuB;AAC7C,SAAO,MAAM,QAAQ,SAAS,EAAE;AAClC;AAWA,eAAsB,eACpB,OACA,UACuB;AACvB,QAAM,YAAY,eAAe,KAAK;AACtC,QAAM,MAAM,GAAG,cAAc,cAAc,SAAS;AAEpD,MAAI;AACF,UAAM,WAAW,MAAM,MAAM,KAAK;AAAA,MAChC,SAAS,EAAE,cAAc,WAAA;AAAA,IAAW,CACrC;AAED,QAAI,CAAC,SAAS,IAAI;AAChB,aAAO;AAAA,QACL,SAAS;AAAA,QACT,OAAO,QAAQ,SAAS,MAAM,IAAI,SAAS,UAAU;AAAA,MAAA;AAAA,IAEzD;AAEA,UAAM,cAAc,SAAS,QAAQ,IAAI,cAAc;AACvD,QAAI,CAAC,sBAAsB,WAAW,GAAG;AACvC,aAAO;AAAA,QACL,SAAS;AAAA,QACT,OAAO,4BAA4B,eAAe,MAAM;AAAA,MAAA;AAAA,IAE5D;AAEA,UAAM,OAAO,MAAM,SAAS,KAAA;AAE5B,UAAM,MAAM,QAAQ,QAAQ,GAAG,EAAE,WAAW,MAAM;AAClD,UAAM,UAAU,UAAU,MAAM,OAAO;AAEvC,WAAO,EAAE,SAAS,MAAM,MAAM,OAAO,WAAW,IAAI,EAAA;AAAA,EACtD,SAAS,KAAK;AACZ,WAAO;AAAA,MACL,SAAS;AAAA,MACT,OAAO,eAAe,QAAQ,IAAI,UAAU,OAAO,GAAG;AAAA,IAAA;AAAA,EAE1D;AACF;"}

package/dist/fulltext/meta.d.ts

@@ -1,25 +0,0 @@
-import { FulltextMeta, FileInfo } from './types.js';
-export interface CreateMetaOptions {
-    citationKey: string;
-    uuid: string;
-    title: string;
-    doi?: string;
-    pmid?: string;
-    pmcid?: string;
-    arxivId?: string;
-    authors?: string;
-    year?: string;
-}
-/** Create a new FulltextMeta object. */
-export declare function createMeta(options: CreateMetaOptions): FulltextMeta;
-/** Load and parse a meta.json file. */
-export declare function loadMeta(path: string): Promise<FulltextMeta>;
-/** Save a FulltextMeta to a meta.json file with 2-space indentation. */
-export declare function saveMeta(path: string, meta: FulltextMeta): Promise<void>;
-/** Update the files section of a FulltextMeta, preserving existing files. */
-export declare function updateMetaFiles(meta: FulltextMeta, files: {
-    pdf?: FileInfo;
-    xml?: FileInfo;
-    markdown?: FileInfo;
-}): FulltextMeta;
-//# sourceMappingURL=meta.d.ts.map

package/dist/fulltext/meta.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"meta.d.ts","sourceRoot":"","sources":["../../src/fulltext/meta.ts"],"names":[],"mappings":"AAAA;;GAEG;AAGH,OAAO,KAAK,EAAE,YAAY,EAAE,QAAQ,EAAE,MAAM,YAAY,CAAC;AAEzD,MAAM,WAAW,iBAAiB;IAChC,WAAW,EAAE,MAAM,CAAC;IACpB,IAAI,EAAE,MAAM,CAAC;IACb,KAAK,EAAE,MAAM,CAAC;IACd,GAAG,CAAC,EAAE,MAAM,CAAC;IACb,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,IAAI,CAAC,EAAE,MAAM,CAAC;CACf;AAED,wCAAwC;AACxC,wBAAgB,UAAU,CAAC,OAAO,EAAE,iBAAiB,GAAG,YAAY,CAmBnE;AAED,uCAAuC;AACvC,wBAAsB,QAAQ,CAAC,IAAI,EAAE,MAAM,GAAG,OAAO,CAAC,YAAY,CAAC,CAGlE;AAED,wEAAwE;AACxE,wBAAsB,QAAQ,CAAC,IAAI,EAAE,MAAM,EAAE,IAAI,EAAE,YAAY,GAAG,OAAO,CAAC,IAAI,CAAC,CAG9E;AAED,6EAA6E;AAC7E,wBAAgB,eAAe,CAC7B,IAAI,EAAE,YAAY,EAClB,KAAK,EAAE;IAAE,GAAG,CAAC,EAAE,QAAQ,CAAC;IAAC,GAAG,CAAC,EAAE,QAAQ,CAAC;IAAC,QAAQ,CAAC,EAAE,QAAQ,CAAA;CAAE,GAC7D,YAAY,CAUd"}

package/dist/fulltext/meta.js.map

@@ -1 +0,0 @@
-{"version":3,"file":"meta.js","sources":["../../src/fulltext/meta.ts"],"sourcesContent":["/**\n * Meta.json management for fulltext article directories.\n */\n\nimport { readFile, writeFile } from 'node:fs/promises';\nimport type { FulltextMeta, FileInfo } from './types.js';\n\nexport interface CreateMetaOptions {\n  citationKey: string;\n  uuid: string;\n  title: string;\n  doi?: string;\n  pmid?: string;\n  pmcid?: string;\n  arxivId?: string;\n  authors?: string;\n  year?: string;\n}\n\n/** Create a new FulltextMeta object. */\nexport function createMeta(options: CreateMetaOptions): FulltextMeta {\n  const uuid8 = options.uuid.slice(0, 8);\n  const meta: FulltextMeta = {\n    dirName: `${options.citationKey}-${uuid8}`,\n    citationKey: options.citationKey,\n    uuid: options.uuid,\n    title: options.title,\n    oaStatus: 'unchecked',\n    files: {},\n  };\n\n  if (options.doi !== undefined) meta.doi = options.doi;\n  if (options.pmid !== undefined) meta.pmid = options.pmid;\n  if (options.pmcid !== undefined) meta.pmcid = options.pmcid;\n  if (options.arxivId !== undefined) meta.arxivId = options.arxivId;\n  if (options.authors !== undefined) meta.authors = options.authors;\n  if (options.year !== undefined) meta.year = options.year;\n\n  return meta;\n}\n\n/** Load and parse a meta.json file. */\nexport async function loadMeta(path: string): Promise<FulltextMeta> {\n  const raw = await readFile(path, 'utf-8');\n  return JSON.parse(raw) as FulltextMeta;\n}\n\n/** Save a FulltextMeta to a meta.json file with 2-space indentation. */\nexport async function saveMeta(path: string, meta: FulltextMeta): Promise<void> {\n  const json = JSON.stringify(meta, null, 2);\n  await writeFile(path, json + '\\n', 'utf-8');\n}\n\n/** Update the files section of a FulltextMeta, preserving existing files. */\nexport function updateMetaFiles(\n  meta: FulltextMeta,\n  files: { pdf?: FileInfo; xml?: FileInfo; markdown?: FileInfo },\n): FulltextMeta {\n  return {\n    ...meta,\n    files: {\n      ...meta.files,\n      ...Object.fromEntries(\n        Object.entries(files).filter(([, v]) => v !== undefined),\n      ),\n    },\n  };\n}\n"],"names":[],"mappings":";AAoBO,SAAS,WAAW,SAA0C;AACnE,QAAM,QAAQ,QAAQ,KAAK,MAAM,GAAG,CAAC;AACrC,QAAM,OAAqB;AAAA,IACzB,SAAS,GAAG,QAAQ,WAAW,IAAI,KAAK;AAAA,IACxC,aAAa,QAAQ;AAAA,IACrB,MAAM,QAAQ;AAAA,IACd,OAAO,QAAQ;AAAA,IACf,UAAU;AAAA,IACV,OAAO,CAAA;AAAA,EAAC;AAGV,MAAI,QAAQ,QAAQ,OAAW,MAAK,MAAM,QAAQ;AAClD,MAAI,QAAQ,SAAS,OAAW,MAAK,OAAO,QAAQ;AACpD,MAAI,QAAQ,UAAU,OAAW,MAAK,QAAQ,QAAQ;AACtD,MAAI,QAAQ,YAAY,OAAW,MAAK,UAAU,QAAQ;AAC1D,MAAI,QAAQ,YAAY,OAAW,MAAK,UAAU,QAAQ;AAC1D,MAAI,QAAQ,SAAS,OAAW,MAAK,OAAO,QAAQ;AAEpD,SAAO;AACT;AAGA,eAAsB,SAAS,MAAqC;AAClE,QAAM,MAAM,MAAM,SAAS,MAAM,OAAO;AACxC,SAAO,KAAK,MAAM,GAAG;AACvB;AAGA,eAAsB,SAAS,MAAc,MAAmC;AAC9E,QAAM,OAAO,KAAK,UAAU,MAAM,MAAM,CAAC;AACzC,QAAM,UAAU,MAAM,OAAO,MAAM,OAAO;AAC5C;AAGO,SAAS,gBACd,MACA,OACc;AACd,SAAO;AAAA,IACL,GAAG;AAAA,IACH,OAAO;AAAA,MACL,GAAG,KAAK;AAAA,MACR,GAAG,OAAO;AAAA,QACR,OAAO,QAAQ,KAAK,EAAE,OAAO,CAAC,GAAG,CAAC,MAAM,MAAM,MAAS;AAAA,MAAA;AAAA,IACzD;AAAA,EACF;AAEJ;"}

package/dist/fulltext/paths.d.ts

@@ -1,12 +0,0 @@
-/**
- * Path resolution utilities for fulltext directories.
- */
-/** Get the fulltext root directory for a session. */
-export declare function getFulltextDir(sessionDir: string): string;
-/** Get an article's fulltext directory. */
-export declare function getArticleDir(sessionDir: string, dirName: string): string;
-/** Get the meta.json path for an article. */
-export declare function getMetaPath(sessionDir: string, dirName: string): string;
-/** Get the README.md path for an article. */
-export declare function getReadmePath(sessionDir: string, dirName: string): string;
-//# sourceMappingURL=paths.d.ts.map

package/dist/fulltext/paths.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"paths.d.ts","sourceRoot":"","sources":["../../src/fulltext/paths.ts"],"names":[],"mappings":"AAAA;;GAEG;AAIH,qDAAqD;AACrD,wBAAgB,cAAc,CAAC,UAAU,EAAE,MAAM,GAAG,MAAM,CAEzD;AAED,2CAA2C;AAC3C,wBAAgB,aAAa,CAAC,UAAU,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,GAAG,MAAM,CAEzE;AAED,6CAA6C;AAC7C,wBAAgB,WAAW,CAAC,UAAU,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,GAAG,MAAM,CAEvE;AAED,6CAA6C;AAC7C,wBAAgB,aAAa,CAAC,UAAU,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,GAAG,MAAM,CAEzE"}

package/dist/fulltext/paths.js.map

@@ -1 +0,0 @@
-{"version":3,"file":"paths.js","sources":["../../src/fulltext/paths.ts"],"sourcesContent":["/**\n * Path resolution utilities for fulltext directories.\n */\n\nimport { join } from 'node:path';\n\n/** Get the fulltext root directory for a session. */\nexport function getFulltextDir(sessionDir: string): string {\n  return join(sessionDir, 'fulltext');\n}\n\n/** Get an article's fulltext directory. */\nexport function getArticleDir(sessionDir: string, dirName: string): string {\n  return join(sessionDir, 'fulltext', dirName);\n}\n\n/** Get the meta.json path for an article. */\nexport function getMetaPath(sessionDir: string, dirName: string): string {\n  return join(sessionDir, 'fulltext', dirName, 'meta.json');\n}\n\n/** Get the README.md path for an article. */\nexport function getReadmePath(sessionDir: string, dirName: string): string {\n  return join(sessionDir, 'fulltext', dirName, 'README.md');\n}\n"],"names":[],"mappings":";AAOO,SAAS,eAAe,YAA4B;AACzD,SAAO,KAAK,YAAY,UAAU;AACpC;AAGO,SAAS,cAAc,YAAoB,SAAyB;AACzE,SAAO,KAAK,YAAY,YAAY,OAAO;AAC7C;AAGO,SAAS,YAAY,YAAoB,SAAyB;AACvE,SAAO,KAAK,YAAY,YAAY,SAAS,WAAW;AAC1D;AAGO,SAAS,cAAc,YAAoB,SAAyB;AACzE,SAAO,KAAK,YAAY,YAAY,SAAS,WAAW;AAC1D;"}

package/dist/fulltext/readme.d.ts

@@ -1,4 +0,0 @@
-import { FulltextMeta } from './types.js';
-/** Generate a README.md for an article's fulltext directory. */
-export declare function generateReadme(meta: FulltextMeta): string;
-//# sourceMappingURL=readme.d.ts.map

package/dist/fulltext/readme.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"readme.d.ts","sourceRoot":"","sources":["../../src/fulltext/readme.ts"],"names":[],"mappings":"AAAA;;GAEG;AAEH,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,YAAY,CAAC;AAE/C,gEAAgE;AAChE,wBAAgB,cAAc,CAAC,IAAI,EAAE,YAAY,GAAG,MAAM,CAiEzD"}

package/dist/fulltext/readme.js.map

@@ -1 +0,0 @@
-{"version":3,"file":"readme.js","sources":["../../src/fulltext/readme.ts"],"sourcesContent":["/**\n * README.md template generation for article fulltext directories.\n */\n\nimport type { FulltextMeta } from './types.js';\n\n/** Generate a README.md for an article's fulltext directory. */\nexport function generateReadme(meta: FulltextMeta): string {\n  const lines: string[] = [];\n\n  // Heading\n  lines.push(`# ${meta.citationKey}`);\n  lines.push('');\n  lines.push(`**Title**: ${meta.title}`);\n\n  if (meta.authors) {\n    lines.push(`**Authors**: ${meta.authors}`);\n  }\n  if (meta.year) {\n    lines.push(`**Year**: ${meta.year}`);\n  }\n\n  // Identifiers\n  const identifiers: string[] = [];\n  if (meta.doi) identifiers.push(`- DOI: ${meta.doi}`);\n  if (meta.pmid) identifiers.push(`- PMID: ${meta.pmid}`);\n  if (meta.pmcid) identifiers.push(`- PMC: ${meta.pmcid}`);\n  if (meta.arxivId) identifiers.push(`- arXiv: ${meta.arxivId}`);\n\n  if (identifiers.length > 0) {\n    lines.push('');\n    lines.push('## Identifiers');\n    lines.push('');\n    lines.push(...identifiers);\n  }\n\n  // Download URLs\n  const urls: string[] = [];\n  if (meta.doi) {\n    urls.push(`- Publisher: https://doi.org/${meta.doi}`);\n  }\n  if (meta.pmcid) {\n    const pmcNum = meta.pmcid.replace(/^PMC/i, '');\n    urls.push(`- PMC PDF: https://www.ncbi.nlm.nih.gov/pmc/articles/${meta.pmcid}/pdf/`);\n    urls.push(`- PMC XML: https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pmc&id=${pmcNum}`);\n  }\n  if (meta.arxivId) {\n    urls.push(`- arXiv PDF: https://arxiv.org/pdf/${meta.arxivId}.pdf`);\n  }\n\n  if (urls.length > 0) {\n    lines.push('');\n    lines.push('## Download URLs');\n    lines.push('');\n    lines.push(...urls);\n  }\n\n  // Instructions\n  lines.push('');\n  lines.push('## Instructions');\n  lines.push('');\n  lines.push('Place fulltext files in this directory:');\n  lines.push('- `fulltext.pdf` - PDF version');\n  lines.push('- `fulltext.md` - Markdown version (optional)');\n  lines.push('');\n  lines.push('After adding files, run:');\n  lines.push('```');\n  lines.push('search-hub fulltext sync <session-id>');\n  lines.push('```');\n  lines.push('');\n\n  return lines.join('\\n');\n}\n"],"names":[],"mappings":"AAOO,SAAS,eAAe,MAA4B;AACzD,QAAM,QAAkB,CAAA;AAGxB,QAAM,KAAK,KAAK,KAAK,WAAW,EAAE;AAClC,QAAM,KAAK,EAAE;AACb,QAAM,KAAK,cAAc,KAAK,KAAK,EAAE;AAErC,MAAI,KAAK,SAAS;AAChB,UAAM,KAAK,gBAAgB,KAAK,OAAO,EAAE;AAAA,EAC3C;AACA,MAAI,KAAK,MAAM;AACb,UAAM,KAAK,aAAa,KAAK,IAAI,EAAE;AAAA,EACrC;AAGA,QAAM,cAAwB,CAAA;AAC9B,MAAI,KAAK,IAAK,aAAY,KAAK,UAAU,KAAK,GAAG,EAAE;AACnD,MAAI,KAAK,KAAM,aAAY,KAAK,WAAW,KAAK,IAAI,EAAE;AACtD,MAAI,KAAK,MAAO,aAAY,KAAK,UAAU,KAAK,KAAK,EAAE;AACvD,MAAI,KAAK,QAAS,aAAY,KAAK,YAAY,KAAK,OAAO,EAAE;AAE7D,MAAI,YAAY,SAAS,GAAG;AAC1B,UAAM,KAAK,EAAE;AACb,UAAM,KAAK,gBAAgB;AAC3B,UAAM,KAAK,EAAE;AACb,UAAM,KAAK,GAAG,WAAW;AAAA,EAC3B;AAGA,QAAM,OAAiB,CAAA;AACvB,MAAI,KAAK,KAAK;AACZ,SAAK,KAAK,gCAAgC,KAAK,GAAG,EAAE;AAAA,EACtD;AACA,MAAI,KAAK,OAAO;AACd,UAAM,SAAS,KAAK,MAAM,QAAQ,SAAS,EAAE;AAC7C,SAAK,KAAK,wDAAwD,KAAK,KAAK,OAAO;AACnF,SAAK,KAAK,kFAAkF,MAAM,EAAE;AAAA,EACtG;AACA,MAAI,KAAK,SAAS;AAChB,SAAK,KAAK,sCAAsC,KAAK,OAAO,MAAM;AAAA,EACpE;AAEA,MAAI,KAAK,SAAS,GAAG;AACnB,UAAM,KAAK,EAAE;AACb,UAAM,KAAK,kBAAkB;AAC7B,UAAM,KAAK,EAAE;AACb,UAAM,KAAK,GAAG,IAAI;AAAA,EACpB;AAGA,QAAM,KAAK,EAAE;AACb,QAAM,KAAK,iBAAiB;AAC5B,QAAM,KAAK,EAAE;AACb,QAAM,KAAK,yCAAyC;AACpD,QAAM,KAAK,gCAAgC;AAC3C,QAAM,KAAK,+CAA+C;AAC1D,QAAM,KAAK,EAAE;AACb,QAAM,KAAK,0BAA0B;AACrC,QAAM,KAAK,KAAK;AAChB,QAAM,KAAK,uCAAuC;AAClD,QAAM,KAAK,KAAK;AAChB,QAAM,KAAK,EAAE;AAEb,SAAO,MAAM,KAAK,IAAI;AACxB;"}

package/dist/fulltext/types.d.ts

@@ -1,90 +0,0 @@
-/**
- * Fulltext management type definitions.
- * Defines interfaces for article fulltext storage, metadata, and indexing.
- */
-/**
- * Information about a retrieved or manually added file.
- */
-export interface FileInfo {
-    /** Fixed filename: "fulltext.pdf", "fulltext.xml", or "fulltext.md" */
-    filename: string;
-    /** How the file was obtained: "pmc", "arxiv", "unpaywall", "manual", etc. */
-    source: string;
-    /** ISO 8601 timestamp when the file was retrieved/added */
-    retrievedAt: string;
-    /** File size in bytes */
-    size?: number;
-    /** For markdown: source file it was converted from (e.g., "fulltext.xml") */
-    convertedFrom?: string;
-}
-/**
- * An Open Access location discovered for an article.
- */
-export interface OALocation {
-    /** Discovery source */
-    source: 'unpaywall' | 'pmc' | 'arxiv' | 'core' | 'publisher';
-    /** URL to the fulltext */
-    url: string;
-    /** Type of content at the URL */
-    urlType: 'pdf' | 'xml' | 'html' | 'repository';
-    /** Version of the article */
-    version: 'published' | 'accepted' | 'submitted';
-    /** License identifier (e.g., "cc-by") */
-    license?: string;
-}
-/**
- * OA status of an article.
- */
-export type OAStatus = 'open' | 'closed' | 'unknown' | 'unchecked';
-/**
- * Metadata for a single article's fulltext directory (meta.json).
- */
-export interface FulltextMeta {
-    /** Directory name: "{citationKey}-{uuid8}" */
-    dirName: string;
-    /** Citation key: e.g., "smith2024" */
-    citationKey: string;
-    /** Full UUID for uniqueness */
-    uuid: string;
-    doi?: string;
-    pmid?: string;
-    pmcid?: string;
-    arxivId?: string;
-    /** Article title */
-    title: string;
-    /** Authors as a display string */
-    authors?: string;
-    /** Publication year */
-    year?: string;
-    /** Current OA status */
-    oaStatus: OAStatus;
-    /** Discovered OA locations */
-    oaLocations?: OALocation[];
-    /** ISO 8601 timestamp of last OA check */
-    checkedAt?: string;
-    files: {
-        pdf?: FileInfo;
-        xml?: FileInfo;
-        markdown?: FileInfo;
-    };
-    pendingDownload?: {
-        suggestedUrls: string[];
-        /** ISO 8601 timestamp */
-        addedAt: string;
-    };
-}
-/**
- * Fulltext reference stored in ArticleEntry (reviews.yaml extension).
- * Links an article in reviews.yaml to its fulltext directory.
- */
-export interface ArticleFulltextRef {
-    /** Directory name: "{citationKey}-{uuid8}" — links to fulltext/<dirName>/ */
-    dirName: string;
-    /** Which file types are available */
-    hasFiles: {
-        pdf: boolean;
-        xml: boolean;
-        markdown: boolean;
-    };
-}
-//# sourceMappingURL=types.d.ts.map

package/dist/fulltext/types.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"types.d.ts","sourceRoot":"","sources":["../../src/fulltext/types.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAEH;;GAEG;AACH,MAAM,WAAW,QAAQ;IACvB,uEAAuE;IACvE,QAAQ,EAAE,MAAM,CAAC;IACjB,6EAA6E;IAC7E,MAAM,EAAE,MAAM,CAAC;IACf,2DAA2D;IAC3D,WAAW,EAAE,MAAM,CAAC;IACpB,yBAAyB;IACzB,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,6EAA6E;IAC7E,aAAa,CAAC,EAAE,MAAM,CAAC;CACxB;AAED;;GAEG;AACH,MAAM,WAAW,UAAU;IACzB,uBAAuB;IACvB,MAAM,EAAE,WAAW,GAAG,KAAK,GAAG,OAAO,GAAG,MAAM,GAAG,WAAW,CAAC;IAC7D,0BAA0B;IAC1B,GAAG,EAAE,MAAM,CAAC;IACZ,iCAAiC;IACjC,OAAO,EAAE,KAAK,GAAG,KAAK,GAAG,MAAM,GAAG,YAAY,CAAC;IAC/C,6BAA6B;IAC7B,OAAO,EAAE,WAAW,GAAG,UAAU,GAAG,WAAW,CAAC;IAChD,yCAAyC;IACzC,OAAO,CAAC,EAAE,MAAM,CAAC;CAClB;AAED;;GAEG;AACH,MAAM,MAAM,QAAQ,GAAG,MAAM,GAAG,QAAQ,GAAG,SAAS,GAAG,WAAW,CAAC;AAEnE;;GAEG;AACH,MAAM,WAAW,YAAY;IAC3B,8CAA8C;IAC9C,OAAO,EAAE,MAAM,CAAC;IAChB,sCAAsC;IACtC,WAAW,EAAE,MAAM,CAAC;IACpB,+BAA+B;IAC/B,IAAI,EAAE,MAAM,CAAC;IAGb,GAAG,CAAC,EAAE,MAAM,CAAC;IACb,IAAI,CAAC,EAAE,MAAM,CAAC;IACd,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,OAAO,CAAC,EAAE,MAAM,CAAC;IAGjB,oBAAoB;IACpB,KAAK,EAAE,MAAM,CAAC;IACd,kCAAkC;IAClC,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB,uBAAuB;IACvB,IAAI,CAAC,EAAE,MAAM,CAAC;IAGd,wBAAwB;IACxB,QAAQ,EAAE,QAAQ,CAAC;IACnB,8BAA8B;IAC9B,WAAW,CAAC,EAAE,UAAU,EAAE,CAAC;IAC3B,0CAA0C;IAC1C,SAAS,CAAC,EAAE,MAAM,CAAC;IAGnB,KAAK,EAAE;QACL,GAAG,CAAC,EAAE,QAAQ,CAAC;QACf,GAAG,CAAC,EAAE,QAAQ,CAAC;QACf,QAAQ,CAAC,EAAE,QAAQ,CAAC;KACrB,CAAC;IAGF,eAAe,CAAC,EAAE;QAChB,aAAa,EAAE,MAAM,EAAE,CAAC;QACxB,yBAAyB;QACzB,OAAO,EAAE,MAAM,CAAC;KACjB,CAAC;CACH;AAED;;;GAGG;AACH,MAAM,WAAW,kBAAkB;IACjC,6EAA6E;IAC7E,OAAO,EAAE,MAAM,CAAC;IAChB,qCAAqC;IACrC,QAAQ,EAAE;QACR,GAAG,EAAE,OAAO,CAAC;QACb,GAAG,EAAE,OAAO,CAAC;QACb,QAAQ,EAAE,OAAO,CAAC;KACnB,CAAC;CACH"}