openalex-local 0.1.0__py3-none-any.whl → 0.3.1__py3-none-any.whl

openalex_local/__init__.py

@@ -8,7 +8,58 @@ Example:
     >>> work = get("10.1038/nature12373")  # or DOI
 """
 
-__version__ = "0.1.0"
+__version__ = "0.3.1"
 
-# API will be exposed here after implementation
-# from .api import search, get, count, info
+from ._core import (
+    SUPPORTED_FORMATS,
+    SearchResult,
+    Work,
+    configure,
+    count,
+    enrich,
+    enrich_ids,
+    exists,
+    get,
+    get_many,
+    get_mode,
+    info,
+    save,
+    search,
+)
+
+# Jobs module (public functions only)
+from . import jobs
+
+# Async module
+from . import aio
+
+# Cache module
+from . import cache
+
+__all__ = [
+    # Core functions
+    "search",
+    "count",
+    "get",
+    "get_many",
+    "exists",
+    "info",
+    # Enrich functions
+    "enrich",
+    "enrich_ids",
+    # Configuration
+    "configure",
+    "get_mode",
+    # Models
+    "Work",
+    "SearchResult",
+    # Export
+    "save",
+    "SUPPORTED_FORMATS",
+    # Jobs
+    "jobs",
+    # Async
+    "aio",
+    # Cache
+    "cache",
+]

openalex_local/__main__.py

@@ -0,0 +1,6 @@
+"""Allow running as python -m openalex_local."""
+
+from .cli import main
+
+if __name__ == "__main__":
+    main()

openalex_local/_cache/__init__.py

@@ -0,0 +1,45 @@
+"""Cache module for openalex_local.
+
+Provides local caching of search results and works for offline analysis.
+
+Example:
+    >>> from openalex_local import cache
+    >>> # Create a cache from search
+    >>> info = cache.create("ml_papers", query="machine learning", limit=1000)
+    >>> print(f"Cached {info.count} papers")
+    >>>
+    >>> # Query the cache
+    >>> papers = cache.query("ml_papers", year_min=2020)
+    >>> # Get IDs for further processing
+    >>> ids = cache.query_ids("ml_papers")
+"""
+
+from .models import CacheInfo
+from .core import (
+    create,
+    append,
+    load,
+    query,
+    query_ids,
+    stats,
+    info,
+    exists,
+    list_caches,
+    delete,
+)
+from .export import export
+
+__all__ = [
+    "CacheInfo",
+    "create",
+    "append",
+    "load",
+    "query",
+    "query_ids",
+    "stats",
+    "info",
+    "exists",
+    "list_caches",
+    "delete",
+    "export",
+]

openalex_local/_cache/core.py

@@ -0,0 +1,298 @@
+"""Core cache operations."""
+
+import json
+from datetime import datetime
+from pathlib import Path
+from typing import Any, Dict, List, Optional
+
+from .models import CacheInfo
+from .utils import (
+    ensure_cache_dir,
+    get_cache_dir,
+    get_cache_path,
+    validate_cache_name,
+)
+
+
+def _load_cache_raw(name: str) -> Dict[str, Any]:
+    """Load raw cache data."""
+    path = get_cache_path(name)
+    if not path.exists():
+        raise FileNotFoundError(f"Cache not found: {name}")
+    with open(path, "r", encoding="utf-8") as f:
+        return json.load(f)
+
+
+def _save_cache_raw(name: str, data: Dict[str, Any]) -> Path:
+    """Save raw cache data."""
+    ensure_cache_dir()
+    path = get_cache_path(name)
+    with open(path, "w", encoding="utf-8") as f:
+        json.dump(data, f, ensure_ascii=False, indent=2)
+    return path
+
+
+def create(
+    name: str,
+    query: Optional[str] = None,
+    ids: Optional[List[str]] = None,
+    papers: Optional[List[Dict]] = None,
+    limit: int = 1000,
+) -> CacheInfo:
+    """
+    Create a new cache.
+
+    Args:
+        name: Cache name (will be sanitized for filesystem)
+        query: Search query to populate cache
+        ids: List of OpenAlex IDs or DOIs to cache
+        papers: Pre-fetched paper dictionaries to cache
+        limit: Maximum papers to cache from query
+
+    Returns:
+        CacheInfo with cache details
+    """
+    from .. import search, get_many
+
+    error = validate_cache_name(name)
+    if error:
+        raise ValueError(error)
+
+    works_data = []
+    queries = []
+
+    if query:
+        results = search(query, limit=limit)
+        works_data.extend([w.to_dict() for w in results.works])
+        queries.append(query)
+
+    if ids:
+        works = get_many(ids)
+        works_data.extend([w.to_dict() for w in works])
+
+    if papers:
+        works_data.extend(papers)
+
+    # Remove duplicates by openalex_id
+    seen = set()
+    unique_works = []
+    for w in works_data:
+        oid = w.get("openalex_id")
+        if oid and oid not in seen:
+            seen.add(oid)
+            unique_works.append(w)
+
+    now = datetime.utcnow().isoformat()
+    cache_data = {
+        "name": name,
+        "created_at": now,
+        "updated_at": now,
+        "queries": queries,
+        "works": unique_works,
+    }
+
+    path = _save_cache_raw(name, cache_data)
+
+    return CacheInfo(
+        name=name,
+        path=str(path),
+        count=len(unique_works),
+        created_at=now,
+        updated_at=now,
+        queries=queries,
+        size_bytes=path.stat().st_size,
+    )
+
+
+def append(
+    name: str,
+    query: Optional[str] = None,
+    ids: Optional[List[str]] = None,
+    limit: int = 1000,
+) -> CacheInfo:
+    """Append works to an existing cache."""
+    from .. import search, get_many
+
+    cache_data = _load_cache_raw(name)
+    existing_ids = {w.get("openalex_id") for w in cache_data.get("works", [])}
+
+    new_works = []
+    queries = cache_data.get("queries", [])
+
+    if query:
+        results = search(query, limit=limit)
+        for w in results.works:
+            if w.openalex_id not in existing_ids:
+                new_works.append(w.to_dict())
+                existing_ids.add(w.openalex_id)
+        if query not in queries:
+            queries.append(query)
+
+    if ids:
+        works = get_many(ids)
+        for w in works:
+            if w.openalex_id not in existing_ids:
+                new_works.append(w.to_dict())
+                existing_ids.add(w.openalex_id)
+
+    cache_data["works"].extend(new_works)
+    cache_data["queries"] = queries
+    cache_data["updated_at"] = datetime.utcnow().isoformat()
+
+    path = _save_cache_raw(name, cache_data)
+
+    return CacheInfo(
+        name=name,
+        path=str(path),
+        count=len(cache_data["works"]),
+        created_at=cache_data.get("created_at", ""),
+        updated_at=cache_data["updated_at"],
+        queries=queries,
+        size_bytes=path.stat().st_size,
+    )
+
+
+def load(name: str) -> List[Dict]:
+    """Load all works from a cache."""
+    cache_data = _load_cache_raw(name)
+    return cache_data.get("works", [])
+
+
+def query(
+    name: str,
+    fields: Optional[List[str]] = None,
+    year_min: Optional[int] = None,
+    year_max: Optional[int] = None,
+    cited_min: Optional[int] = None,
+    has_abstract: Optional[bool] = None,
+    is_oa: Optional[bool] = None,
+    source: Optional[str] = None,
+    limit: Optional[int] = None,
+) -> List[Dict]:
+    """Query a cache with filters."""
+    works = load(name)
+    results = []
+
+    for w in works:
+        if year_min and (w.get("year") or 0) < year_min:
+            continue
+        if year_max and (w.get("year") or 9999) > year_max:
+            continue
+        if cited_min and (w.get("cited_by_count") or 0) < cited_min:
+            continue
+        if has_abstract is not None:
+            has_abs = bool(w.get("abstract"))
+            if has_abstract != has_abs:
+                continue
+        if is_oa is not None and w.get("is_oa") != is_oa:
+            continue
+        if source and source.lower() not in (w.get("source") or "").lower():
+            continue
+
+        if fields:
+            w = {k: w.get(k) for k in fields}
+
+        results.append(w)
+
+        if limit and len(results) >= limit:
+            break
+
+    return results
+
+
+def query_ids(name: str) -> List[str]:
+    """Get all OpenAlex IDs from a cache."""
+    works = load(name)
+    return [w.get("openalex_id") for w in works if w.get("openalex_id")]
+
+
+def stats(name: str) -> Dict[str, Any]:
+    """Get statistics for a cache."""
+    cache_data = _load_cache_raw(name)
+    works = cache_data.get("works", [])
+
+    if not works:
+        return {
+            "name": name, "total": 0, "year_min": None, "year_max": None,
+            "citations_total": 0, "citations_mean": 0,
+            "with_abstract": 0, "open_access": 0, "sources": [],
+        }
+
+    years = [w.get("year") for w in works if w.get("year")]
+    citations = [w.get("cited_by_count") or 0 for w in works]
+    abstracts = sum(1 for w in works if w.get("abstract"))
+    oa_count = sum(1 for w in works if w.get("is_oa"))
+
+    source_counts: Dict[str, int] = {}
+    for w in works:
+        src = w.get("source")
+        if src:
+            source_counts[src] = source_counts.get(src, 0) + 1
+    top_sources = sorted(source_counts.items(), key=lambda x: -x[1])[:10]
+
+    return {
+        "name": name,
+        "total": len(works),
+        "year_min": min(years) if years else None,
+        "year_max": max(years) if years else None,
+        "citations_total": sum(citations),
+        "citations_mean": sum(citations) / len(works) if works else 0,
+        "with_abstract": abstracts,
+        "with_abstract_pct": round(100 * abstracts / len(works), 1) if works else 0,
+        "open_access": oa_count,
+        "open_access_pct": round(100 * oa_count / len(works), 1) if works else 0,
+        "sources": top_sources,
+        "queries": cache_data.get("queries", []),
+        "created_at": cache_data.get("created_at"),
+        "updated_at": cache_data.get("updated_at"),
+    }
+
+
+def info(name: str) -> CacheInfo:
+    """Get cache info."""
+    path = get_cache_path(name)
+    if not path.exists():
+        raise FileNotFoundError(f"Cache not found: {name}")
+
+    cache_data = _load_cache_raw(name)
+
+    return CacheInfo(
+        name=name,
+        path=str(path),
+        count=len(cache_data.get("works", [])),
+        created_at=cache_data.get("created_at", ""),
+        updated_at=cache_data.get("updated_at", ""),
+        queries=cache_data.get("queries", []),
+        size_bytes=path.stat().st_size,
+    )
+
+
+def exists(name: str) -> bool:
+    """Check if a cache exists."""
+    return get_cache_path(name).exists()
+
+
+def list_caches() -> List[CacheInfo]:
+    """List all caches."""
+    cache_dir = get_cache_dir()
+    if not cache_dir.exists():
+        return []
+
+    caches = []
+    for path in cache_dir.glob("*.json"):
+        try:
+            cache_info = info(path.stem)
+            caches.append(cache_info)
+        except (json.JSONDecodeError, KeyError):
+            continue
+
+    return sorted(caches, key=lambda c: c.updated_at, reverse=True)
+
+
+def delete(name: str) -> bool:
+    """Delete a cache."""
+    path = get_cache_path(name)
+    if path.exists():
+        path.unlink()
+        return True
+    return False

openalex_local/_cache/export.py

@@ -0,0 +1,100 @@
+"""Cache export functionality."""
+
+import csv
+import json
+from pathlib import Path
+from typing import List, Dict
+
+from .core import load
+
+
+def export(
+    name: str,
+    output_path: str,
+    format: str = "json",
+) -> str:
+    """
+    Export a cache to a file.
+
+    Args:
+        name: Cache name
+        output_path: Output file path
+        format: Export format ("json", "csv", "bibtex")
+
+    Returns:
+        Path to exported file
+    """
+    works = load(name)
+    output = Path(output_path)
+
+    if format == "json":
+        _export_json(works, output)
+    elif format == "csv":
+        _export_csv(works, output)
+    elif format == "bibtex":
+        _export_bibtex(works, output)
+    else:
+        raise ValueError(f"Unknown format: {format}. Use 'json', 'csv', or 'bibtex'")
+
+    return str(output)
+
+
+def _export_json(works: List[Dict], output: Path) -> None:
+    """Export to JSON format."""
+    with open(output, "w", encoding="utf-8") as f:
+        json.dump(works, f, ensure_ascii=False, indent=2)
+
+
+def _export_csv(works: List[Dict], output: Path) -> None:
+    """Export to CSV format."""
+    if not works:
+        output.write_text("")
+        return
+
+    # Get all unique keys
+    keys = set()
+    for w in works:
+        keys.update(w.keys())
+
+    # Prioritize common fields
+    priority = ["openalex_id", "doi", "title", "authors", "year", "source", "cited_by_count"]
+    fieldnames = [k for k in priority if k in keys]
+    fieldnames.extend(sorted(k for k in keys if k not in priority))
+
+    with open(output, "w", encoding="utf-8", newline="") as f:
+        writer = csv.DictWriter(f, fieldnames=fieldnames, extrasaction="ignore")
+        writer.writeheader()
+        for w in works:
+            row = {}
+            for k, v in w.items():
+                if isinstance(v, list):
+                    row[k] = "; ".join(str(x) for x in v)
+                else:
+                    row[k] = v
+            writer.writerow(row)
+
+
+def _export_bibtex(works: List[Dict], output: Path) -> None:
+    """Export to BibTeX format."""
+    from .._core.models import Work
+
+    lines = []
+    for w in works:
+        work = Work(
+            openalex_id=w.get("openalex_id", ""),
+            doi=w.get("doi"),
+            title=w.get("title"),
+            authors=w.get("authors", []),
+            year=w.get("year"),
+            source=w.get("source"),
+            volume=w.get("volume"),
+            issue=w.get("issue"),
+            pages=w.get("pages"),
+            publisher=w.get("publisher"),
+            type=w.get("type"),
+            oa_url=w.get("oa_url"),
+        )
+        lines.append(work.citation("bibtex"))
+        lines.append("")
+
+    output.write_text("\n".join(lines), encoding="utf-8")

openalex_local/_cache/models.py

@@ -0,0 +1,17 @@
+"""Cache data models."""
+
+from dataclasses import dataclass, field
+from typing import List
+
+
+@dataclass
+class CacheInfo:
+    """Information about a cache."""
+
+    name: str
+    path: str
+    count: int
+    created_at: str
+    updated_at: str
+    queries: List[str] = field(default_factory=list)
+    size_bytes: int = 0

openalex_local/_cache/utils.py

@@ -0,0 +1,85 @@
+"""Cache utilities for openalex_local."""
+
+import os
+import re
+from pathlib import Path
+from typing import Optional
+
+# Default cache directory
+DEFAULT_CACHE_DIR = Path.home() / ".openalex_local" / "caches"
+
+
+def get_cache_dir() -> Path:
+    """Get cache directory from environment or default."""
+    env_dir = os.environ.get("OPENALEX_LOCAL_CACHE_DIR")
+    if env_dir:
+        return Path(env_dir)
+    return DEFAULT_CACHE_DIR
+
+
+def sanitize_cache_name(name: str) -> str:
+    """
+    Sanitize cache name for filesystem safety.
+
+    Args:
+        name: Raw cache name
+
+    Returns:
+        Sanitized cache name
+
+    Example:
+        >>> sanitize_cache_name("my cache/name!")
+        'my_cache_name_'
+    """
+    # Replace non-alphanumeric characters (except - and _) with underscore
+    sanitized = re.sub(r"[^a-zA-Z0-9_-]", "_", name)
+    # Remove leading/trailing underscores
+    sanitized = sanitized.strip("_")
+    # Limit length
+    if len(sanitized) > 100:
+        sanitized = sanitized[:100]
+    # Ensure not empty
+    if not sanitized:
+        sanitized = "cache"
+    return sanitized
+
+
+def get_cache_path(name: str) -> Path:
+    """
+    Get full path to cache file.
+
+    Args:
+        name: Cache name
+
+    Returns:
+        Path to cache JSON file
+    """
+    cache_dir = get_cache_dir()
+    safe_name = sanitize_cache_name(name)
+    return cache_dir / f"{safe_name}.json"
+
+
+def ensure_cache_dir() -> Path:
+    """Ensure cache directory exists."""
+    cache_dir = get_cache_dir()
+    cache_dir.mkdir(parents=True, exist_ok=True)
+    return cache_dir
+
+
+def validate_cache_name(name: str) -> Optional[str]:
+    """
+    Validate cache name and return error message if invalid.
+
+    Args:
+        name: Cache name to validate
+
+    Returns:
+        Error message if invalid, None if valid
+    """
+    if not name:
+        return "Cache name cannot be empty"
+    if len(name) > 100:
+        return "Cache name too long (max 100 characters)"
+    if name.startswith("."):
+        return "Cache name cannot start with '.'"
+    return None

openalex_local/_cli/__init__.py

@@ -0,0 +1,9 @@
+#!/usr/bin/env python3
+"""Internal CLI modules."""
+
+from .cli import cli, main
+from .mcp import mcp, run_mcp_server
+
+__all__ = ["cli", "main", "mcp", "run_mcp_server"]
+
+# EOF