genesis/tools.py

# genesis/tools.py
"""
Utility functions for GENESIS-AI
"""

import re
from datetime import datetime

def extract_citations(text):
    """Extracts DOI, PMID, and URLs from text."""
    citations = []
    doi_pattern = r"(10\.\d{4,9}/[-._;()/:A-Z0-9]+)"
    pmid_pattern = r"PMID:\s*(\d+)"
    url_pattern = r"(https?://[^\s)]+)"

    for match in re.finditer(doi_pattern, text, re.IGNORECASE):
        citations.append({"type": "DOI", "id": match.group(1), "url": f"https://doi.org/{match.group(1)}"})
    for match in re.finditer(pmid_pattern, text, re.IGNORECASE):
        citations.append({"type": "PMID", "id": match.group(1), "url": f"https://pubmed.ncbi.nlm.nih.gov/{match.group(1)}/"})
    for match in re.finditer(url_pattern, text, re.IGNORECASE):
        if not any(c["url"] == match.group(1) for c in citations):
            citations.append({"type": "URL", "id": "", "url": match.group(1)})
    return citations

def timestamp():
    """Returns current UTC timestamp as ISO string."""
    return datetime.utcnow().isoformat()