stack/dev/scripts/check_pdf_coverage.py

"""Check PDF retrieval coverage for skin substitute evidence base.

Reports how many Zotero items have PDF attachments vs DOI-bearing items
that could potentially be retrieved. Run after using Zotero's
"Find Available PDF" with the scipdf plugin.

Usage:
    uv run python dev/scripts/check_pdf_coverage.py
"""

from __future__ import annotations

import sqlite3
from pathlib import Path

from conf import path as conf_path

ZOTERO_DB = str(conf_path("db.zotero"))


def main() -> None:
    print("Checking PDF coverage for skin-subs items in Zotero ...\n")

    con = sqlite3.connect(ZOTERO_DB, timeout=10)
    con.row_factory = sqlite3.Row

    # Total skin-subs items
    total = con.execute("""
        SELECT count(DISTINCT it.itemID) FROM itemTags it
        JOIN tags t ON it.tagID = t.tagID
        WHERE t.name = 'module:skin-subs'
    """).fetchone()[0]

    # Items with DOI (retrievable)
    with_doi = con.execute("""
        SELECT count(DISTINCT i.itemID) FROM items i
        JOIN itemTags it ON i.itemID = it.itemID
        JOIN tags t ON it.tagID = t.tagID
        JOIN itemData id ON i.itemID = id.itemID
        WHERE t.name = 'module:skin-subs' AND id.fieldID = {FIELD_MAP['DOI']}
    """).fetchone()[0]

    # Items with PDF attachments
    with_pdf = con.execute("""
        SELECT count(DISTINCT parent.itemID) FROM items parent
        JOIN itemTags it ON parent.itemID = it.itemID
        JOIN tags t ON it.tagID = t.tagID
        JOIN itemAttachments ia ON ia.parentItemID = parent.itemID
        JOIN items att ON ia.itemID = att.itemID
        WHERE t.name = 'module:skin-subs'
          AND ia.contentType = 'application/pdf'
    """).fetchone()[0]

    print(f"Total skin-subs items:     {total:>6}")
    print(f"Items with DOI:            {with_doi:>6} ({with_doi * 100 // total}%)")
    print(
        f"Items with PDF attached:   {with_pdf:>6} ({with_pdf * 100 // max(total, 1)}%)"
    )
    print(f"DOIs without PDF:          {with_doi - with_pdf:>6}")
    print(f"Coverage (of DOI items):   {with_pdf * 100 // max(with_doi, 1)}%")

    # Breakdown by item type
    print("\nBy item type:")
    for r in con.execute("""
        SELECT it2.typeName,
               count(DISTINCT i.itemID) as total,
               count(DISTINCT CASE WHEN ia.itemID IS NOT NULL THEN i.itemID END) as with_pdf
        FROM items i
        JOIN itemTags it ON i.itemID = it.itemID
        JOIN tags t ON it.tagID = t.tagID
        JOIN itemTypes it2 ON i.itemTypeID = it2.itemTypeID
        LEFT JOIN itemAttachments ia ON ia.parentItemID = i.itemID
            AND ia.contentType = 'application/pdf'
        WHERE t.name = 'module:skin-subs'
        GROUP BY it2.typeName
        ORDER BY total DESC
    """).fetchall():
        pct = r["with_pdf"] * 100 // max(r["total"], 1)
        print(
            f"  {r['typeName']:20s}  total={r['total']:>5}  pdf={r['with_pdf']:>5}  ({pct}%)"
        )

    # Storage size
    storage = Path(conf_path("storage.zotero"))
    if storage.exists():
        total_bytes = sum(f.stat().st_size for f in storage.rglob("*") if f.is_file())
        print(f"\nZotero storage size: {total_bytes / 1024 / 1024:.1f} MB")

    con.close()
    print("\nTo retrieve PDFs: open Zotero, select 'Skin Substitutes' collection,")
    print("select all items (Ctrl+A), right-click → Find Available PDF.")
    print("scipdf plugin (v8.0.4) will try Unpaywall then 7 SciHub mirrors.")


if __name__ == "__main__":
    main()