ira/execution/api_handlers/openalex_handler.py

"""
OpenAlex API handler.
Provides access to academic research papers and scholarly information.
"""

import os
import requests
from typing import Dict, List, Any, Optional

from .base_handler import BaseSearchHandler
from config.config import get_config, get_api_key


class OpenAlexSearchHandler(BaseSearchHandler):
    """Handler for OpenAlex academic search API."""

    def __init__(self):
        """Initialize the OpenAlex search handler."""
        self.config = get_config()
        # OpenAlex doesn't require an API key, but using an email is recommended
        self.email = self.config.config_data.get("academic_search", {}).get("email", "user@example.com")
        self.base_url = "https://api.openalex.org/works"
        self.available = True  # OpenAlex doesn't require an API key
        
        # Get any custom settings from config
        self.academic_config = self.config.config_data.get("academic_search", {}).get("openalex", {})

    def search(self, query: str, num_results: int = 10, **kwargs) -> List[Dict[str, Any]]:
        """
        Execute a search query using OpenAlex.
        
        Args:
            query: The search query to execute
            num_results: Number of results to return
            **kwargs: Additional search parameters:
                - filter_type: Filter by work type (article, book, etc.)
                - filter_year: Filter by publication year or range
                - filter_open_access: Only return open access publications
                - sort: Sort by relevance, citations, publication date
                - filter_concept: Filter by academic concept/field
        
        Returns:
            List of search results with standardized format
        """
        # Build the search URL with parameters
        params = {
            "search": query,
            "per_page": num_results,
            "mailto": self.email  # Good practice for the API
        }
        
        # Add filters
        filters = []
        
        # Type filter (article, book, etc.)
        if "filter_type" in kwargs:
            filters.append(f"type.id:{kwargs['filter_type']}")
        
        # Year filter
        if "filter_year" in kwargs:
            filters.append(f"publication_year:{kwargs['filter_year']}")
        
        # Open access filter
        if kwargs.get("filter_open_access", False):
            filters.append("is_oa:true")
        
        # Concept/field filter
        if "filter_concept" in kwargs:
            filters.append(f"concepts.id:{kwargs['filter_concept']}")
        
        # Combine filters if there are any
        if filters:
            params["filter"] = ",".join(filters)
        
        # Sort parameter
        if "sort" in kwargs:
            params["sort"] = kwargs["sort"]
        else:
            # Default to sorting by relevance score
            params["sort"] = "relevance_score:desc"
        
        try:
            # Make the request
            response = requests.get(self.base_url, params=params)
            response.raise_for_status()
            
            # Parse the response
            data = response.json()
            
            # Process the results
            results = []
            for item in data.get("results", []):
                # Extract authors
                authors = []
                for author in item.get("authorships", [])[:3]:
                    author_name = author.get("author", {}).get("display_name", "")
                    if author_name:
                        authors.append(author_name)
                
                # Format citation count
                citation_count = item.get("cited_by_count", 0)
                
                # Get the publication year
                pub_year = item.get("publication_year", "Unknown")
                
                # Check if it's open access
                is_oa = item.get("open_access", {}).get("is_oa", False)
                oa_status = "Open Access" if is_oa else "Subscription"
                
                # Get journal/venue name
                journal = None
                if "primary_location" in item and item["primary_location"]:
                    source = item.get("primary_location", {}).get("source", {})
                    if source:
                        journal = source.get("display_name", "Unknown Journal")
                
                # Get DOI
                doi = item.get("doi")
                url = f"https://doi.org/{doi}" if doi else item.get("url", "")
                
                # Get abstract
                abstract = item.get("abstract_inverted_index", None)
                snippet = ""
                
                # Convert abstract_inverted_index to readable text if available
                if abstract:
                    try:
                        # The OpenAlex API uses an inverted index format
                        # We need to reconstruct the text from this format
                        words = {}
                        for word, positions in abstract.items():
                            for pos in positions:
                                words[pos] = word
                        
                        # Reconstruct the abstract from the positions
                        snippet = " ".join([words.get(i, "") for i in sorted(words.keys())])
                    except:
                        snippet = "Abstract not available in readable format"
                
                # Fallback if no abstract is available
                if not snippet:
                    snippet = f"Academic paper: {item.get('title', 'Untitled')}. Published in {journal or 'Unknown'} ({pub_year}). {citation_count} citations."
                
                # Create the result
                result = {
                    "title": item.get("title", "Untitled"),
                    "url": url,
                    "snippet": snippet,
                    "source": "openalex",
                    "authors": ", ".join(authors),
                    "year": pub_year,
                    "citation_count": citation_count,
                    "access_status": oa_status,
                    "journal": journal,
                    "doi": doi
                }
                
                results.append(result)
            
            return results
            
        except requests.exceptions.RequestException as e:
            print(f"Error executing OpenAlex search: {e}")
            return []

    def get_name(self) -> str:
        """Get the name of the search handler."""
        return "openalex"

    def is_available(self) -> bool:
        """Check if the OpenAlex API is available."""
        return self.available

    def get_rate_limit_info(self) -> Dict[str, Any]:
        """Get information about the API's rate limits."""
        return {
            "requests_per_minute": 100,  # OpenAlex is quite generous with rate limits
            "requests_per_day": 100000,  # 100k requests per day for anonymous users
            "current_usage": None  # OpenAlex doesn't provide usage info in responses
        }