openrxiv-utils 0.0.0

package/src/biorxiv-parser.spec.ts

@@ -0,0 +1,258 @@
+import { describe, it, expect } from 'vitest';
+import {
+  extractDOIFromURL,
+  parseDOI,
+  extractBaseDOI,
+  extractVersion,
+  isValidBiorxivDOI,
+  isValidBiorxivURL,
+  parseBiorxivURL,
+} from './biorxiv-parser.js';
+
+describe('BioRxiv URL Parser', () => {
+  describe('extractDOIFromURL', () => {
+    it.each([
+      [
+        'https://www.biorxiv.org/content/10.1101/2024.01.25.577295v3',
+        '10.1101/2024.01.25.577295v3',
+      ],
+      [
+        'https://www.medrxiv.org/content/10.1101/2020.03.19.20039131v2',
+        '10.1101/2020.03.19.20039131v2',
+      ],
+      [
+        'https://www.biorxiv.org/content/10.1101/2024.01.25.577295v3.article-info',
+        '10.1101/2024.01.25.577295v3',
+      ],
+      [
+        'https://www.biorxiv.org/content/10.1101/2024.01.25.577295v3.full',
+        '10.1101/2024.01.25.577295v3',
+      ],
+      [
+        'https://www.biorxiv.org/content/10.1101/2024.01.25.577295v3.abstract',
+        '10.1101/2024.01.25.577295v3',
+      ],
+      [
+        'https://www.biorxiv.org/content/10.1101/2024.01.25.577295v3.pdf',
+        '10.1101/2024.01.25.577295v3',
+      ],
+      [
+        'https://www.biorxiv.org/content/10.1101/2024.01.25.577295v3.suppl',
+        '10.1101/2024.01.25.577295v3',
+      ],
+      ['https://doi.org/10.1101/2024.01.25.577295v3', '10.1101/2024.01.25.577295v3'],
+      ['10.1101/2024.01.25.577295v3', '10.1101/2024.01.25.577295v3'],
+    ])('should extract DOI from standard content URL', (url, expected) => {
+      const result = extractDOIFromURL(url);
+      expect(result).toBe(expected);
+    });
+
+    it.each([
+      ['https://example.com/not-biorxiv', null],
+      ['https://biorxiv.org/invalid-path', null],
+      ['not-a-url', null],
+      ['', null],
+      ['https://biorxiv.org/', null],
+    ])('should return null for invalid URLs', (url, expected) => {
+      const result = extractDOIFromURL(url);
+      expect(result).toBe(expected);
+    });
+  });
+
+  describe('parseDOI', () => {
+    it('should parse DOI with version', () => {
+      const doi = '10.1101/2024.01.25.577295v3';
+      const result = parseDOI(doi);
+
+      expect(result).toEqual({
+        doi: '10.1101/2024.01.25.577295v3',
+        prefix: '10.1101',
+        date: '2024-01-25',
+        identifier: '577295',
+        suffix: '2024.01.25.577295',
+        version: 'v3',
+      });
+    });
+
+    it('should parse DOI without version', () => {
+      const doi = '10.1101/2024.01.25.577295';
+      const result = parseDOI(doi);
+
+      expect(result).toEqual({
+        doi: '10.1101/2024.01.25.577295',
+        prefix: '10.1101',
+        date: '2024-01-25',
+        identifier: '577295',
+        suffix: '2024.01.25.577295',
+        version: null,
+      });
+    });
+
+    it('should parse DOI with single digit month and day', () => {
+      const doi = '10.1101/2024.01.05.123456v1';
+      const result = parseDOI(doi);
+
+      expect(result).toEqual({
+        doi: '10.1101/2024.01.05.123456v1',
+        prefix: '10.1101',
+        date: '2024-01-05',
+        identifier: '123456',
+        suffix: '2024.01.05.123456',
+        version: 'v1',
+      });
+    });
+
+    it('should return null for invalid DOI format', () => {
+      const invalidDOIs = [
+        '10.1000/123.456.789',
+        '10.1101/2024.1.25.577295',
+        '10.1101/2024.01.25.57729',
+        '10.1101/2024.01.25.5772955666',
+        '10.1101/2024.01.25.577295v',
+        '10.1101/2024.01.25.577295v',
+        'invalid-doi',
+        '',
+      ];
+
+      invalidDOIs.forEach((doi) => {
+        const result = parseDOI(doi);
+        expect(result).toBeNull();
+      });
+    });
+  });
+
+  describe('extractBaseDOI', () => {
+    it.each([
+      ['10.1101/2024.01.25.577295', '10.1101/2024.01.25.577295'], // Same DOI
+      ['10.1101/2024.01.25.577295v3', '10.1101/2024.01.25.577295'], // Remove version
+      ['10.1101/2024.01.25.577295v12', '10.1101/2024.01.25.577295'], // Remove double digit version
+      ['10.1101/2020.03.19.20039131v2', '10.1101/2020.03.19.20039131'], // medrxiv variant
+    ])('should extract base DOI from versioned DOI', (doi, expected) => {
+      const result = extractBaseDOI(doi);
+      expect(result).toBe(expected);
+    });
+  });
+
+  describe('extractVersion', () => {
+    it.each([
+      ['10.1101/2024.01.25.577295v3', '3'],
+      ['10.1101/2024.01.25.577295', null],
+      ['10.1101/2024.01.25.577295v12', '12'],
+    ])('should extract version from DOI', (doi, expected) => {
+      const result = extractVersion(doi);
+      expect(result).toBe(expected);
+    });
+  });
+
+  describe('isValidBiorxivDOI', () => {
+    it.each([
+      // Valid DOIs
+      ['10.1101/2024.01.25.577295v3', true],
+      ['10.1101/2024.01.25.577295', true],
+      ['10.1101/2020.01.15.123456v2', true],
+      ['10.1101/2018.01.15.789012', true],
+      ['10.1101/789012', true],
+      ['10.1101/789012v12', true],
+      ['10.1101/789012v3', true],
+      ['10.1101/2020.03.19.20039131v2', true],
+      ['10.1101/2024.1.25.577295', false],
+      ['10.1101/2024.01.25.57729', false],
+      ['invalid-doi', false],
+      ['10.1101/78901', false],
+      ['10.1101/78901v3', false],
+      ['', false],
+    ])('should validate correct bioRxiv DOIs %s', (doi, expected) => {
+      const result = isValidBiorxivDOI(doi);
+      expect(result).toBe(expected);
+    });
+  });
+
+  describe('isValidBiorxivURL', () => {
+    it.each([
+      ['https://www.biorxiv.org/content/10.1101/2024.01.25.577295v3', true],
+      ['https://www.biorxiv.org/content/10.1101/2024.01.25.577295v3.article-info', true],
+      ['https://doi.org/10.1101/2024.01.25.577295v3', true],
+      ['10.1101/2024.01.25.577295v3', true],
+      ['https://www.biorxiv.org/content/10.1101/486050v2.article-info', true],
+      ['https://www.biorxiv.org/content/10.1101/486050', true],
+      // Invalid
+      ['https://example.com/not-biorxiv', false],
+      ['https://biorxiv.org/invalid-path', false],
+      ['10.1000/123.456.789', false],
+      ['invalid-url', false],
+      ['', false],
+    ])('should validate correct bioRxiv URLs', (url, expected) => {
+      const result = isValidBiorxivURL(url);
+      expect(result).toBe(expected);
+    });
+  });
+
+  describe('parseBiorxivURL', () => {
+    it('should parse valid bioRxiv URL', () => {
+      const url = 'https://www.biorxiv.org/content/10.1101/2024.01.25.577295v3.article-info';
+      const result = parseBiorxivURL(url);
+
+      expect(result).toEqual({
+        doi: '10.1101/2024.01.25.577295v3',
+        baseDOI: '10.1101/2024.01.25.577295',
+        version: '3',
+        fullURL: url,
+        isValid: true,
+      });
+    });
+
+    it('should parse URL without version', () => {
+      const url = 'https://www.biorxiv.org/content/10.1101/2024.01.25.577295';
+      const result = parseBiorxivURL(url);
+
+      expect(result).toEqual({
+        doi: '10.1101/2024.01.25.577295',
+        baseDOI: '10.1101/2024.01.25.577295',
+        version: null,
+        fullURL: url,
+        isValid: true,
+      });
+    });
+
+    it('should return null for invalid URL', () => {
+      const url = 'https://example.com/not-biorxiv';
+      const result = parseBiorxivURL(url);
+      expect(result).toBeNull();
+    });
+  });
+
+  describe('Edge Cases', () => {
+    it('should handle DOIs with leading zeros in month/day', () => {
+      const doi = '10.1101/2024.01.05.123456v1';
+      const result = parseDOI(doi);
+
+      expect(result).toEqual({
+        doi: '10.1101/2024.01.05.123456v1',
+        prefix: '10.1101',
+        date: '2024-01-05',
+        identifier: '123456',
+        suffix: '2024.01.05.123456',
+        version: 'v1',
+      });
+    });
+
+    it('should handle DOIs with different identifier lengths', () => {
+      const doi = '10.1101/2024.01.25.123456v1';
+      const result = parseDOI(doi);
+
+      expect(result?.identifier).toBe('123456');
+    });
+
+    it('should handle URLs with query parameters', () => {
+      const url = 'https://www.biorxiv.org/content/10.1101/2024.01.25.577295v3?query=test';
+      const result = extractDOIFromURL(url);
+      expect(result).toBe('10.1101/2024.01.25.577295v3');
+    });
+
+    it('should handle URLs with fragments', () => {
+      const url = 'https://www.biorxiv.org/content/10.1101/2024.01.25.577295v3#section';
+      const result = extractDOIFromURL(url);
+      expect(result).toBe('10.1101/2024.01.25.577295v3');
+    });
+  });
+});

package/src/biorxiv-parser.ts

@@ -0,0 +1,161 @@
+/**
+ * Utility functions for parsing bioRxiv URLs and DOIs
+ */
+
+export interface ParsedBiorxivURL {
+  doi: string;
+  baseDOI: string;
+  version: string | null;
+  fullURL: string;
+  isValid: boolean;
+}
+
+export interface DOIParts {
+  doi: string;
+  prefix: string;
+  suffix: string;
+  date: string | null;
+  identifier: string;
+  version: string | null;
+}
+
+/**
+ * Extract DOI from a bioRxiv URL
+ */
+export function extractDOIFromURL(url: string): string | null {
+  // Handle various bioRxiv URL formats
+  let doi = null;
+
+  // Check for bioRxiv content URLs
+  if (url.includes('biorxiv.org/content/')) {
+    const match = url.match(/biorxiv\.org\/content\/([^?#]+)/);
+    if (match && match[1]) {
+      doi = match[1];
+    }
+  }
+  // Check for medRxiv content URLs
+  else if (url.includes('medrxiv.org/content/')) {
+    const match = url.match(/medrxiv\.org\/content\/([^?#]+)/);
+    if (match && match[1]) {
+      doi = match[1];
+    }
+  }
+  // Check for doi.org redirects
+  else if (url.includes('doi.org/')) {
+    const match = url.match(/doi\.org\/([^?#]+)/);
+    if (match && match[1]) {
+      doi = match[1];
+    }
+  }
+  // Check for direct DOI input
+  else if (url.startsWith('10.1101/')) {
+    doi = url;
+  }
+
+  if (doi) {
+    // Clean up the extracted DOI (remove any trailing extensions)
+    return doi.replace(/\.(article-info|full|abstract|pdf|suppl)$/, '');
+  }
+
+  return null;
+}
+
+/**
+ * Parse a bioRxiv DOI into its components
+ * Supports both legacy numeric format (2019 and earlier) and current date-based format (2019+)
+ */
+export function parseDOI(doi: string): DOIParts | null {
+  // Handle current date-based format (2019+): 10.1101/YYYY.MM.DD.XXXXXXvN
+  const currentPattern = /^10\.1101\/(\d{4})\.(\d{2})\.(\d{2})\.(\d{6,8})(v\d+)?$/;
+  const currentMatch = doi.match(currentPattern);
+
+  if (currentMatch) {
+    const [prefix, suffix] = doi.split('/');
+    const [, year, month, day, identifier, version] = currentMatch;
+    const date = `${year}-${month}-${day}`;
+
+    return {
+      doi,
+      prefix,
+      suffix: suffix.replace(/(v\d+)$/, ''),
+      date,
+      identifier,
+      version: version || null,
+    };
+  }
+
+  // Handle legacy numeric format (2019 and earlier): 10.1101/XXXXXX
+  const legacyPattern = /^10\.1101\/(\d{6,8})(v\d+)?$/;
+  const legacyMatch = doi.match(legacyPattern);
+
+  if (legacyMatch) {
+    const [prefix, suffix] = doi.split('/');
+    const [, identifier, version] = legacyMatch;
+    return {
+      doi,
+      prefix,
+      suffix: suffix.replace(/(v\d+)$/, ''),
+      date: null,
+      identifier,
+      version: version || null,
+    };
+  }
+
+  return null;
+}
+
+/**
+ * Extract base DOI (without version)
+ * Works with both legacy numeric and current date-based formats
+ */
+export function extractBaseDOI(doi: string): string {
+  // Remove version suffix if present
+  return doi.replace(/v\d+$/, '');
+}
+
+/**
+ * Extract version from DOI
+ * Works with both legacy numeric and current date-based formats
+ */
+export function extractVersion(doi: string): string | null {
+  const match = doi.match(/v(\d+)$/);
+  return match ? match[1] : null;
+}
+
+/**
+ * Check if a DOI is a valid bioRxiv DOI
+ * Supports both legacy numeric and current date-based formats
+ */
+export function isValidBiorxivDOI(doi: string): boolean {
+  return parseDOI(doi) !== null;
+}
+
+/**
+ * Check if a URL is a valid bioRxiv URL
+ */
+export function isValidBiorxivURL(url: string): boolean {
+  const doi = extractDOIFromURL(url);
+  return doi !== null && isValidBiorxivDOI(doi);
+}
+
+/**
+ * Parse a bioRxiv URL and extract all relevant information
+ */
+export function parseBiorxivURL(url: string): ParsedBiorxivURL | null {
+  const doi = extractDOIFromURL(url);
+
+  if (!doi || !isValidBiorxivDOI(doi)) {
+    return null;
+  }
+
+  const baseDOI = extractBaseDOI(doi);
+  const version = extractVersion(doi);
+
+  return {
+    doi,
+    baseDOI,
+    version,
+    fullURL: url,
+    isValid: true,
+  };
+}