add seed registry, tag vocabulary (measure/seed/program), and Zotero library cleanup

- Tag.measure(), Tag.seed(), Tag.program() factory methods - dev/scripts/register_seeds.py: declarative registry mapping 34 seed files to source URLs, titles, and tags with bidirectional Zotero sync - Zotero library standardization: authors on 2451/2504 items, CFR titles from eCFR API (630 sections with headings, 15 cross-title corrections), 1070 URL-as-title items resolved to real page titles - openpyxl + pdfplumber dev deps for seed file inspection
2026-03-03 23:49:07 -05:00
parent f66b35f5fe
commit 421ce48fd8
4 changed files with 860 additions and 0 deletions
--- a/dev/scripts/register_seeds.py
+++ b/dev/scripts/register_seeds.py
@@ -0,0 +1,667 @@
 """Register dev/seeds/ files in bib.sqlite and Zotero.
 Each seed file gets a parent ``download`` item (with source URL) in
 bib.sqlite, an attachment linking the file, and the ``seed:true`` tag.
 Items are also pushed to Zotero so the seed tag appears there too.
 Usage::
    uv run python dev/scripts/register_seeds.py            # register all
    uv run python dev/scripts/register_seeds.py --dry-run   # preview only
    uv run python dev/scripts/register_seeds.py --pull       # Zotero → dev/seeds/
 """
 from __future__ import annotations
 import argparse
 import random
 import shutil
 import sqlite3
 import string
 import subprocess
 from dataclasses import dataclass, field
 from datetime import datetime, timezone
 from pathlib import Path
 SEEDS_DIR = Path("dev/seeds")
 BIB_DB = "data/bib.sqlite"
 ZOTERO_DB = "zotero/data/zotero.sqlite"
 ZOTERO_STORAGE = Path("zotero/data/storage")
 # Zotero schema constants (match add_carrier_to_zotero.py / sync.py)
 ZOTERO_TYPE_WEBPAGE = 40
 ZOTERO_TYPE_ATTACHMENT = 3
 ZOTERO_FIELD_TITLE = 1
 ZOTERO_FIELD_URL = 10
 ZOTERO_FIELD_DATE = 6
 ZOTERO_FIELD_ACCESS_DATE = 11
 ZOTERO_FIELD_WEBSITE_TYPE = 42
 ZOTERO_FIELD_WEBSITE_TITLE = 123
 SEED_TAG = "seed:true"
@dataclass
 class SeedSpec:
    """Maps a seed file to its provenance metadata."""
    path: str
    url: str
    title: str
    tags: list[str] = field(default_factory=list)
 # ── Registry ─────────────────────────────────────────────────────
 SEED_REGISTRY: tuple[SeedSpec, ...] = (
    # --- CCLF ---
    SeedSpec(
        path="cclf-information-packet.pdf",
        url="https://www.cms.gov/files/document/cclf-information-packet.pdf",
        title="CCLF Information Packet",
        tags=["module:aco", "source:cms-website"],
    ),
    SeedSpec(
        path="cclf_ip_v41.pdf",
        url="https://www.cms.gov/files/document/cclf-file-data-elements.pdf",
        title="CCLF Information Packet v41",
        tags=["module:aco", "source:cms-website"],
    ),
    SeedSpec(
        path="CCLF Uses and Limitations v4.pdf",
        url="https://www.cms.gov/files/document/uses-and-limitations-cclfs.pdf",
        title="CCLF Uses and Limitations v4",
        tags=["module:aco", "source:cms-website"],
    ),
    # --- CCW ---
    SeedSpec(
        path="codebook-ffs-claims.pdf",
        url="https://www2.ccwdata.org/documents/10280/19022436/codebook-ffs-claims.pdf",
        title="CCW Codebook — FFS Claims",
        tags=["module:ccw", "source:cms-website"],
    ),
    SeedSpec(
        path="record-layout-ffs-claims.xlsx",
        url="https://www2.ccwdata.org/documents/10280/19022436/record-layout-ffs-claims.xlsx",
        title="CCW Record Layout — FFS Claims",
        tags=["module:ccw", "source:cms-website"],
    ),
    # --- ACO REACH ---
    SeedSpec(
        path="ACO_REACH_bulk_upload_participants 5-19 (1).xlsx",
        url="https://innovation.cms.gov/innovation-models/aco-reach",
        title="ACO REACH Bulk Upload Participants Template",
        tags=["module:aco", "program:reach", "source:cms-website"],
    ),
    SeedSpec(
        path="ACO_REACH_Calendar_updated_02032026.xlsx",
        url="https://innovation.cms.gov/innovation-models/aco-reach",
        title="ACO REACH Calendar (Updated 2026-02-03)",
        tags=["module:aco", "program:reach", "source:cms-website"],
    ),
    SeedSpec(
        path="ACOREACH_DataReportingImplementationGuide_v1.3_updated_508.pdf",
        url="https://innovation.cms.gov/innovation-models/aco-reach",
        title="ACO REACH Data Reporting Implementation Guide v1.3",
        tags=["module:aco", "program:reach", "source:cms-website"],
    ),
    SeedSpec(
        path="ACOREACHM.FNCL.ER.IP.4.01.01_Clean.pdf",
        url="https://innovation.cms.gov/innovation-models/aco-reach",
        title="ACO REACH Financial — Expenditure Report IP",
        tags=["module:aco", "program:reach", "source:cms-website"],
    ),
    SeedSpec(
        path="ACOReachQualityStrategyPaperPY2023_03-18-2024.pdf",
        url="https://innovation.cms.gov/innovation-models/aco-reach",
        title="ACO REACH Quality Strategy Paper PY2023",
        tags=[
            "module:aco",
            "program:reach",
            "year:2023",
            "source:cms-website",
        ],
    ),
    SeedSpec(
        path="ACOR_Q3 QQR_CoverNotice_Final.docx",
        url="https://innovation.cms.gov/innovation-models/aco-reach",
        title="ACO REACH Q3 QQR Cover Notice",
        tags=["module:aco", "program:reach", "source:cms-website"],
    ),
    SeedSpec(
        path="PY2023 ACO REACH Reporting and Data Sharing Overview_v20232203.pdf",
        url="https://innovation.cms.gov/innovation-models/aco-reach",
        title="PY2023 ACO REACH Reporting and Data Sharing Overview",
        tags=[
            "module:aco",
            "program:reach",
            "year:2023",
            "source:cms-website",
        ],
    ),
    SeedSpec(
        path="Copy of Mock Data File - Beneficiary Alignment Report (1).xlsx",
        url="https://innovation.cms.gov/innovation-models/aco-reach",
        title="ACO REACH Mock Beneficiary Alignment Report",
        tags=["module:aco", "program:reach", "source:cms-website"],
    ),
    # --- Quality Measures ---
    SeedSpec(
        path="PY2025 Quarter2 MedicareCQM Data Dictionary.xlsx",
        url="https://www.cms.gov/medicare/quality/initiatives/shared-savings-program/quality-measures",
        title="PY2025 Q2 Medicare CQM Data Dictionary",
        tags=[
            "module:aco",
            "program:mssp",
            "year:2025",
            "source:cms-website",
        ],
    ),
    SeedSpec(
        path="DataInquiryTemplate_202512_508.xlsx",
        url="https://www.cms.gov/medicare/quality/initiatives/shared-savings-program/quality-measures",
        title="Data Inquiry Template (2025-12)",
        tags=["module:aco", "program:mssp", "year:2025", "source:cms-website"],
    ),
    SeedSpec(
        path="Static Report Crosswalk.xlsx",
        url="https://www.cms.gov/medicare/quality/initiatives/shared-savings-program/quality-measures",
        title="Static Report Crosswalk",
        tags=["module:aco", "program:mssp", "source:cms-website"],
    ),
    # --- SSP / County ---
    SeedSpec(
        path="County-level Aggregate Expenditure and Risk Score Data on Assignable Beneficiaries.zip",
        url="https://data.cms.gov/medicare-shared-savings-program/county-level-aggregate-expenditure-and-risk-score",
        title="SSP County-Level Aggregate Expenditure — Assignable Beneficiaries PUF",
        tags=["module:aco", "program:mssp", "source:cms-website"],
    ),
    SeedSpec(
        path="County_Level_Aggregate_Expenditure_and_Risk_Score_Data_on_Assigned_Beneficiaries_PUF_for_2014-2020.zip",
        url="https://data.cms.gov/medicare-shared-savings-program/county-level-aggregate-expenditure-and-risk-score",
        title="SSP County-Level Aggregate Expenditure — Assigned Beneficiaries PUF 2014-2020",
        tags=["module:aco", "program:mssp", "source:cms-website"],
    ),
    SeedSpec(
        path="County-Level_FFS_Data_for_Shared_Savings_Program_Benchmark_PUF_Methodology-508.pdf",
        url="https://data.cms.gov/medicare-shared-savings-program/county-level-aggregate-expenditure-and-risk-score",
        title="County-Level FFS Data for SSP Benchmark PUF Methodology",
        tags=["module:aco", "program:mssp", "source:cms-website"],
    ),
    SeedSpec(
        path="County_Lvl_FFS_Data_SSP_Benchmark_PUF_Data_Dictionary.pdf",
        url="https://data.cms.gov/medicare-shared-savings-program/county-level-aggregate-expenditure-and-risk-score",
        title="County-Level FFS Data SSP Benchmark PUF Data Dictionary",
        tags=["module:aco", "program:mssp", "source:cms-website"],
    ),
    SeedSpec(
        path="Data Dictionary_ Medicare Shared Savings Program County-Level Aggregate Expenditure and Risk Score Data on Assignable Beneficiaries PUF - County_Lvl_FFS_Data_SSP_Benchmark_PUF_Data_Dictionary.pdf",
        url="https://data.cms.gov/medicare-shared-savings-program/county-level-aggregate-expenditure-and-risk-score",
        title="SSP County-Level PUF Data Dictionary — Assignable Beneficiaries",
        tags=["module:aco", "program:mssp", "source:cms-website"],
    ),
    # --- BCDA ---
    SeedSpec(
        path="BCDA_Data_Dictionary.xlsx",
        url="https://bcda.cms.gov/assets/downloads/BCDA_Data_Dictionary.xlsx",
        title="BCDA Data Dictionary",
        tags=["module:aco", "source:cms-website"],
    ),
    SeedSpec(
        path="BCDA_Partially_Adjudicated_Data_Dictionary.xlsx",
        url="https://bcda.cms.gov/assets/data/BCDA_Partially_Adjudicated_Data_Dictionary.xlsx",
        title="BCDA Partially Adjudicated Data Dictionary",
        tags=["module:aco", "source:cms-website"],
    ),
    SeedSpec(
        path="unmapped-fields-between-cclf-and-bcda.xlsx",
        url="https://bcda.cms.gov/assets/downloads/unmapped-fields-between-cclf-and-bcda.xlsx",
        title="Unmapped Fields Between CCLF and BCDA",
        tags=["module:aco", "source:cms-website"],
    ),
    # --- BCDA v2 (directory) ---
    SeedSpec(
        path="bcda_v2",
        url="https://bcda.cms.gov/api/v2",
        title="BCDA API v2 Response Samples",
        tags=["module:aco", "source:cms-website"],
    ),
    # --- BCDA NDJSON samples ---
    SeedSpec(
        path="Coverage.ndjson",
        url="https://bcda.cms.gov/assets/data/Coverage.ndjson",
        title="BCDA Sample — Coverage NDJSON",
        tags=["module:aco", "source:cms-website"],
    ),
    SeedSpec(
        path="ExplanationOfBenefit.ndjson",
        url="https://bcda.cms.gov/assets/data/ExplanationOfBenefit.ndjson",
        title="BCDA Sample — ExplanationOfBenefit NDJSON",
        tags=["module:aco", "source:cms-website"],
    ),
    SeedSpec(
        path="Patient.ndjson",
        url="https://bcda.cms.gov/assets/data/Patient.ndjson",
        title="BCDA Sample — Patient NDJSON",
        tags=["module:aco", "source:cms-website"],
    ),
    # --- ALR/ASR ---
    SeedSpec(
        path="ALRASRGuide.pdf",
        url="https://innovation.cms.gov/innovation-models/aco-reach",
        title="ALR/ASR Guide",
        tags=["module:aco", "program:reach", "source:cms-website"],
    ),
    # --- PY2023 (directory) ---
    SeedSpec(
        path="PY2023",
        url="https://innovation.cms.gov/innovation-models/aco-reach",
        title="PY2023 ACO REACH Mock Data and Templates",
        tags=[
            "module:aco",
            "program:reach",
            "year:2023",
            "source:cms-website",
        ],
    ),
    SeedSpec(
        path="PY2023 Templates.zip",
        url="https://innovation.cms.gov/innovation-models/aco-reach",
        title="PY2023 ACO REACH Templates (ZIP)",
        tags=[
            "module:aco",
            "program:reach",
            "year:2023",
            "source:cms-website",
        ],
    ),
    # --- Grafana (directory) ---
    SeedSpec(
        path="grafana",
        url="",
        title="Grafana Dashboard Configs",
        tags=["source:internal"],
    ),
    # --- Weekly Claims Reduction ---
    SeedSpec(
        path="Weekly Claims Reduction File Data Dictionary - CMMI-ICD-Appendix-D.docx",
        url="https://innovation.cms.gov/innovation-models/aco-reach",
        title="Weekly Claims Reduction File Data Dictionary (Appendix D)",
        tags=["module:aco", "program:reach", "source:cms-website"],
    ),
    # --- Other ---
    SeedSpec(
        path="Dremio-Apache-Polaris-The-Definitive-Guide.pdf",
        url="https://www.dremio.com/resources/guides/apache-polaris/",
        title="Dremio — Apache Polaris: The Definitive Guide",
        tags=["source:vendor"],
    ),
 )
 # ── Helpers ───────────────────────────────────────────────────────
 def _zotero_key() -> str:
    chars = string.ascii_uppercase + string.digits
    return "".join(random.choices(chars, k=8))  # noqa: S311
 def _now_iso() -> str:
    return datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ")
 def _ensure_value(con: sqlite3.Connection, value: str) -> int:
    row = con.execute(
        "SELECT valueID FROM itemDataValues WHERE value = ?", (value,)
    ).fetchone()
    if row:
        return row[0]
    cur = con.execute(
        "INSERT INTO itemDataValues (value) VALUES (?)", (value,)
    )
    return cur.lastrowid
 def _ensure_tag(con: sqlite3.Connection, name: str) -> int:
    row = con.execute(
        "SELECT tagID FROM tags WHERE name = ?", (name,)
    ).fetchone()
    if row:
        return row[0]
    cur = con.execute("INSERT INTO tags (name) VALUES (?)", (name,))
    return cur.lastrowid
 def _set_zotero_field(
    con: sqlite3.Connection, item_id: int, field_id: int, value: str
 ) -> None:
    if not value:
        return
    value_id = _ensure_value(con, value)
    con.execute(
        "INSERT OR REPLACE INTO itemData (itemID, fieldID, valueID) "
        "VALUES (?, ?, ?)",
        (item_id, field_id, value_id),
    )
 def _content_type(path: Path) -> str:
    ext = path.suffix.lower()
    types = {
        ".pdf": "application/pdf",
        ".xlsx": "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
        ".docx": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
        ".zip": "application/zip",
        ".ndjson": "application/x-ndjson",
        ".csv": "text/csv",
        ".txt": "text/plain",
        ".json": "application/json",
        ".ini": "text/plain",
    }
    return types.get(ext, "application/octet-stream")
 # ── Phase A: tag existing Zotero attachments ──────────────────────
 def tag_existing_zotero(
    con: sqlite3.Connection, spec: SeedSpec, *, dry_run: bool = False
 ) -> bool:
    """Find a Zotero attachment by filename and tag its parent."""
    filename = Path(spec.path).name
    row = con.execute(
        """SELECT ia.parentItemID
           FROM itemAttachments ia
           WHERE ia.path LIKE ?
           LIMIT 1""",
        (f"%{filename}",),
    ).fetchone()
    if not row or not row[0]:
        return False
    parent_id = row[0]
    if dry_run:
        print(f"  [exists] Zotero parent itemID={parent_id}")
        return True
    # Add seed tag + any extra tags
    all_tags = [SEED_TAG] + spec.tags
    for tag_name in all_tags:
        tag_id = _ensure_tag(con, tag_name)
        con.execute(
            "INSERT OR IGNORE INTO itemTags (itemID, tagID, type) "
            "VALUES (?, ?, 0)",
            (parent_id, tag_id),
        )
    return True
 # ── Phase B: create missing Zotero items ──────────────────────────
 def register_in_zotero(
    con: sqlite3.Connection, spec: SeedSpec, *, dry_run: bool = False
 ) -> None:
    """Create a Zotero webpage item + file attachment for a seed."""
    if not spec.url:
        if dry_run:
            print("  [skip-zotero] no URL")
        return
    if dry_run:
        print("  [create] new Zotero webpage item")
        return
    now = _now_iso()
    next_id = con.execute(
        "SELECT COALESCE(MAX(itemID), 0) + 1 FROM items"
    ).fetchone()[0]
    parent_key = _zotero_key()
    # Create parent webpage item
    con.execute(
        """INSERT INTO items
           (itemID, itemTypeID, dateAdded, dateModified,
            key, version, synced, libraryID)
           VALUES (?, ?, ?, ?, ?, 0, 0, 1)""",
        (next_id, ZOTERO_TYPE_WEBPAGE, now, now, parent_key),
    )
    _set_zotero_field(con, next_id, ZOTERO_FIELD_TITLE, spec.title)
    _set_zotero_field(con, next_id, ZOTERO_FIELD_URL, spec.url)
    _set_zotero_field(con, next_id, ZOTERO_FIELD_DATE, now[:10])
    _set_zotero_field(con, next_id, ZOTERO_FIELD_ACCESS_DATE, now)
    _set_zotero_field(
        con, next_id, ZOTERO_FIELD_WEBSITE_TYPE, "Government Data Portal"
    )
    _set_zotero_field(
        con,
        next_id,
        ZOTERO_FIELD_WEBSITE_TITLE,
        "Centers for Medicare & Medicaid Services",
    )
    # Tags
    all_tags = [SEED_TAG] + spec.tags
    for tag_name in all_tags:
        tag_id = _ensure_tag(con, tag_name)
        con.execute(
            "INSERT OR IGNORE INTO itemTags (itemID, tagID, type) "
            "VALUES (?, ?, 0)",
            (next_id, tag_id),
        )
    # Attach file (skip directories)
    seed_path = SEEDS_DIR / spec.path
    if seed_path.is_file():
        att_id = con.execute(
            "SELECT COALESCE(MAX(itemID), 0) + 1 FROM items"
        ).fetchone()[0]
        att_key = _zotero_key()
        # Copy to Zotero storage
        storage_dir = ZOTERO_STORAGE / att_key
        subprocess.run(
            ["sudo", "mkdir", "-p", str(storage_dir)], check=True
        )
        dest = storage_dir / seed_path.name
        subprocess.run(
            ["sudo", "cp", str(seed_path), str(dest)], check=True
        )
        subprocess.run(
            ["sudo", "chown", "-R", "100999:100999", str(storage_dir)],
            check=True,
        )
        con.execute(
            """INSERT INTO items
               (itemID, itemTypeID, dateAdded, dateModified,
                key, version, synced, libraryID)
               VALUES (?, ?, ?, ?, ?, 0, 0, 1)""",
            (att_id, ZOTERO_TYPE_ATTACHMENT, now, now, att_key),
        )
        con.execute(
            """INSERT INTO itemAttachments
               (itemID, parentItemID, linkMode, contentType, path)
               VALUES (?, ?, 0, ?, ?)""",
            (
                att_id,
                next_id,
                _content_type(seed_path),
                f"storage:{seed_path.name}",
            ),
        )
        title_val = _ensure_value(con, seed_path.name)
        con.execute(
            "INSERT INTO itemData (itemID, fieldID, valueID) "
            "VALUES (?, ?, ?)",
            (att_id, ZOTERO_FIELD_TITLE, title_val),
        )
 # ── Phase C: register in bib.sqlite ──────────────────────────────
 def register_in_bib(spec: SeedSpec, *, dry_run: bool = False) -> str:
    """Create a bib item for a seed. Returns the item key."""
    from bib.item import Item
    from bib.store import Store
    if dry_run:
        print("  [bib] would create")
        return ""
    store = Store(BIB_DB)
    tags = [SEED_TAG] + spec.tags
    # Check if this exact title already exists with seed tag
    existing = store.list_items(tag=SEED_TAG, query=spec.title)
    if existing:
        print(f"  [bib] already exists: {existing[0].key}")
        store.close()
        return existing[0].key
    item = Item(
        item_type="download",
        title=spec.title,
        url=spec.url,
        institution="Centers for Medicare & Medicaid Services",
        tags=tags,
    )
    key = store.create(item, tags=None)
    # Attach the file (skip directories)
    seed_path = SEEDS_DIR / spec.path
    if seed_path.is_file():
        store.attach_file(key, seed_path)
    store.close()
    return key
 # ── Pull mode: Zotero → dev/seeds/ ───────────────────────────────
 def pull_from_zotero(*, dry_run: bool = False) -> int:
    """Copy seed-tagged Zotero attachments missing from dev/seeds/."""
    con = sqlite3.connect(ZOTERO_DB, timeout=10)
    rows = con.execute(
        """SELECT ia.path, ia.parentItemID
           FROM itemAttachments ia
           JOIN items i ON ia.itemID = i.itemID
           JOIN itemTags it ON ia.parentItemID = it.itemID
           JOIN tags t ON it.tagID = t.tagID
           WHERE t.name = ?
             AND ia.path IS NOT NULL
             AND ia.linkMode = 0""",
        (SEED_TAG,),
    ).fetchall()
    con.close()
    copied = 0
    for row in rows:
        zpath = row[0]  # "storage:filename"
        if not zpath.startswith("storage:"):
            continue
        filename = zpath[len("storage:"):]
        dest = SEEDS_DIR / filename
        if dest.exists():
            continue
        # Find the file in Zotero storage
        for storage_sub in ZOTERO_STORAGE.iterdir():
            candidate = storage_sub / filename
            if candidate.exists():
                if dry_run:
                    print(f"  [pull] {filename}")
                else:
                    shutil.copy2(candidate, dest)
                    print(f"  pulled {filename}")
                copied += 1
                break
    return copied
 # ── Main ──────────────────────────────────────────────────────────
 def main() -> None:
    parser = argparse.ArgumentParser(
        description="Register dev/seeds/ files in bib & Zotero"
    )
    parser.add_argument(
        "--dry-run",
        action="store_true",
        help="Preview without modifying databases",
    )
    parser.add_argument(
        "--pull",
        action="store_true",
        help="Pull seed-tagged Zotero attachments into dev/seeds/",
    )
    args = parser.parse_args()
    if args.pull:
        print("Pulling seed-tagged attachments from Zotero...")
        n = pull_from_zotero(dry_run=args.dry_run)
        print(f"{'Would copy' if args.dry_run else 'Copied'} {n} files")
        return
    zotero_db_path = Path(ZOTERO_DB)
    has_zotero = zotero_db_path.exists()
    zcon = None
    if has_zotero:
        try:
            zcon = sqlite3.connect(ZOTERO_DB, timeout=10)
            # Test that we can actually read
            zcon.execute("SELECT 1 FROM items LIMIT 1")
        except sqlite3.OperationalError as exc:
            print(f"Zotero DB locked ({exc}), skipping Zotero phases")
            zcon = None
    total = len(SEED_REGISTRY)
    tagged = 0
    created_z = 0
    created_b = 0
    for i, spec in enumerate(SEED_REGISTRY, 1):
        seed_path = SEEDS_DIR / spec.path
        exists = seed_path.exists()
        status = "OK" if exists else "MISSING"
        print(f"[{i}/{total}] {spec.path} [{status}]")
        if not exists:
            print("  [skip] file not found")
            continue
        # Phase A+B: Zotero
        if zcon:
            found = tag_existing_zotero(zcon, spec, dry_run=args.dry_run)
            if found:
                tagged += 1
            else:
                register_in_zotero(zcon, spec, dry_run=args.dry_run)
                created_z += 1
        # Phase C: bib.sqlite
        register_in_bib(spec, dry_run=args.dry_run)
        created_b += 1
    if zcon:
        if not args.dry_run:
            zcon.commit()
        zcon.close()
    label = "Would register" if args.dry_run else "Registered"
    print(f"\n{label}:")
    print(f"  Zotero tagged existing: {tagged}")
    print(f"  Zotero created new:     {created_z}")
    print(f"  Bib items upserted:     {created_b}")
 if __name__ == "__main__":
    main()
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -19,6 +19,8 @@ dev = [
    "coverage>=7.13.4",
    "dbt-core==1.10.15",
    "dbt-duckdb>=1.10,<1.11",
    "openpyxl>=3.1.5",
    "pdfplumber>=0.11.9",
    "polars>=1.38.1",
    "pytest>=9.0.2",
    "pytest-cov>=7.0.0",
--- a/src/bib/tag.py
+++ b/src/bib/tag.py
@@ -131,6 +131,47 @@ class Tag(BaseModel):
        """
        return cls(namespace="sup", value=slug)
    @classmethod
    def measure(cls, measure_id: str) -> Tag:
        """Tag for a CMS quality measure identifier.
        Parameters
        ----------
        measure_id : str
            Short measure code, e.g. ``UAMCC``, ``ACR``, ``HWR``,
            ``MCC``, ``NQF2888``, ``NQF1789``.
        Examples::
            Tag.measure("UAMCC")   # measure:UAMCC
            Tag.measure("ACR")     # measure:ACR
            Tag.measure("HWR")     # measure:HWR
        """
        return cls(namespace="measure", value=measure_id.upper())
    @classmethod
    def seed(cls) -> Tag:
        """Tag marking an item as a dev/seeds/ seed file."""
        return cls(namespace="seed", value="true")
    @classmethod
    def program(cls, program_name: str) -> Tag:
        """Tag for the CMS payment / quality program context.
        Parameters
        ----------
        program_name : str
            Program identifier, e.g. ``reach``, ``mssp``, ``mips``,
            ``vbp``, ``hacrp``.
        Examples::
            Tag.program("reach")   # program:reach
            Tag.program("mssp")    # program:mssp
            Tag.program("mips")    # program:mips
        """
        return cls(namespace="program", value=program_name.lower())
 _RULE_KIND = {"Final": "FR", "Proposed": "PR", "Correction": "CR"}
--- a/uv.lock
+++ b/uv.lock
@@ -568,6 +568,15 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/dd/2d/13e6024e613679d8a489dd922f199ef4b1d08a456a58eadd96dc2f05171f/duckdb-1.4.4-cp314-cp314-win_arm64.whl", hash = "sha256:53cd6423136ab44383ec9955aefe7599b3fb3dd1fe006161e6396d8167e0e0d4", size = 13458633, upload-time = "2026-01-26T11:50:17.657Z" },
 ]
 [[package]]
 name = "et-xmlfile"
 version = "2.0.0"
 source = { registry = "https://pypi.org/simple" }
 sdist = { url = "https://files.pythonhosted.org/packages/d3/38/af70d7ab1ae9d4da450eeec1fa3918940a5fafb9055e934af8d6eb0c2313/et_xmlfile-2.0.0.tar.gz", hash = "sha256:dab3f4764309081ce75662649be815c4c9081e88f0837825f90fd28317d4da54", size = 17234, upload-time = "2024-10-25T17:25:40.039Z" }
 wheels = [
    { url = "https://files.pythonhosted.org/packages/c1/8b/5fe2cc11fee489817272089c4203e679c63b570a5aaeb18d852ae3cbba6a/et_xmlfile-2.0.0-py3-none-any.whl", hash = "sha256:7a91720bc756843502c3b7504c77b8fe44217c85c537d85037f0f536151b2caa", size = 18059, upload-time = "2024-10-25T17:25:39.051Z" },
 ]
 [[package]]
 name = "fsspec"
 version = "2026.2.0"
@@ -875,6 +884,18 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/be/9c/92789c596b8df838baa98fa71844d84283302f7604ed565dafe5a6b5041a/oauthlib-3.3.1-py3-none-any.whl", hash = "sha256:88119c938d2b8fb88561af5f6ee0eec8cc8d552b7bb1f712743136eb7523b7a1", size = 160065, upload-time = "2025-06-19T22:48:06.508Z" },
 ]
 [[package]]
 name = "openpyxl"
 version = "3.1.5"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
    { name = "et-xmlfile" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/3d/f9/88d94a75de065ea32619465d2f77b29a0469500e99012523b91cc4141cd1/openpyxl-3.1.5.tar.gz", hash = "sha256:cf0e3cf56142039133628b5acffe8ef0c12bc902d2aadd3e0fe5878dc08d1050", size = 186464, upload-time = "2024-06-28T14:03:44.161Z" }
 wheels = [
    { url = "https://files.pythonhosted.org/packages/c0/da/977ded879c29cbd04de313843e76868e6e13408a94ed6b987245dc7c8506/openpyxl-3.1.5-py2.py3-none-any.whl", hash = "sha256:5282c12b107bffeef825f4617dc029afaf41d0ea60823bbb665ef3079dc79de2", size = 250910, upload-time = "2024-06-28T14:03:41.161Z" },
 ]
 [[package]]
 name = "orderly-set"
 version = "5.5.0"
@@ -911,6 +932,102 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/cc/20/ff623b09d963f88bfde16306a54e12ee5ea43e9b597108672ff3a408aad6/pathspec-0.12.1-py3-none-any.whl", hash = "sha256:a0d503e138a4c123b27490a4f7beda6a01c6f288df0e4a8b79c7eb0dc7b4cc08", size = 31191, upload-time = "2023-12-10T22:30:43.14Z" },
 ]
 [[package]]
 name = "pdfminer-six"
 version = "20251230"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
    { name = "charset-normalizer" },
    { name = "cryptography" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/46/9a/d79d8fa6d47a0338846bb558b39b9963b8eb2dfedec61867c138c1b17eeb/pdfminer_six-20251230.tar.gz", hash = "sha256:e8f68a14c57e00c2d7276d26519ea64be1b48f91db1cdc776faa80528ca06c1e", size = 8511285, upload-time = "2025-12-30T15:49:13.104Z" }
 wheels = [
    { url = "https://files.pythonhosted.org/packages/65/d7/b288ea32deb752a09aab73c75e1e7572ab2a2b56c3124a5d1eb24c62ceb3/pdfminer_six-20251230-py3-none-any.whl", hash = "sha256:9ff2e3466a7dfc6de6fd779478850b6b7c2d9e9405aa2a5869376a822771f485", size = 6591909, upload-time = "2025-12-30T15:49:10.76Z" },
 ]
 [[package]]
 name = "pdfplumber"
 version = "0.11.9"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
    { name = "pdfminer-six" },
    { name = "pillow" },
    { name = "pypdfium2" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/38/37/9ca3519e92a8434eb93be570b131476cc0a4e840bb39c62ddb7813a39d53/pdfplumber-0.11.9.tar.gz", hash = "sha256:481224b678b2bbdbf376e2c39bf914144eef7c3d301b4a28eebf0f7f6109d6dc", size = 102768, upload-time = "2026-01-05T08:10:29.072Z" }
 wheels = [
    { url = "https://files.pythonhosted.org/packages/8b/c8/cdbc975f5b634e249cfa6597e37c50f3078412474f21c015e508bfbfe3c3/pdfplumber-0.11.9-py3-none-any.whl", hash = "sha256:33ec5580959ba524e9100138746e090879504c42955df1b8a997604dd326c443", size = 60045, upload-time = "2026-01-05T08:10:27.512Z" },
 ]
 [[package]]
 name = "pillow"
 version = "12.1.1"
 source = { registry = "https://pypi.org/simple" }
 sdist = { url = "https://files.pythonhosted.org/packages/1f/42/5c74462b4fd957fcd7b13b04fb3205ff8349236ea74c7c375766d6c82288/pillow-12.1.1.tar.gz", hash = "sha256:9ad8fa5937ab05218e2b6a4cff30295ad35afd2f83ac592e68c0d871bb0fdbc4", size = 46980264, upload-time = "2026-02-11T04:23:07.146Z" }
 wheels = [
    { url = "https://files.pythonhosted.org/packages/07/d3/8df65da0d4df36b094351dce696f2989bec731d4f10e743b1c5f4da4d3bf/pillow-12.1.1-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:ab323b787d6e18b3d91a72fc99b1a2c28651e4358749842b8f8dfacd28ef2052", size = 5262803, upload-time = "2026-02-11T04:20:47.653Z" },
    { url = "https://files.pythonhosted.org/packages/d6/71/5026395b290ff404b836e636f51d7297e6c83beceaa87c592718747e670f/pillow-12.1.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:adebb5bee0f0af4909c30db0d890c773d1a92ffe83da908e2e9e720f8edf3984", size = 4657601, upload-time = "2026-02-11T04:20:49.328Z" },
    { url = "https://files.pythonhosted.org/packages/b1/2e/1001613d941c67442f745aff0f7cc66dd8df9a9c084eb497e6a543ee6f7e/pillow-12.1.1-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:bb66b7cc26f50977108790e2456b7921e773f23db5630261102233eb355a3b79", size = 6234995, upload-time = "2026-02-11T04:20:51.032Z" },
    { url = "https://files.pythonhosted.org/packages/07/26/246ab11455b2549b9233dbd44d358d033a2f780fa9007b61a913c5b2d24e/pillow-12.1.1-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:aee2810642b2898bb187ced9b349e95d2a7272930796e022efaf12e99dccd293", size = 8045012, upload-time = "2026-02-11T04:20:52.882Z" },
    { url = "https://files.pythonhosted.org/packages/b2/8b/07587069c27be7535ac1fe33874e32de118fbd34e2a73b7f83436a88368c/pillow-12.1.1-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:a0b1cd6232e2b618adcc54d9882e4e662a089d5768cd188f7c245b4c8c44a397", size = 6349638, upload-time = "2026-02-11T04:20:54.444Z" },
    { url = "https://files.pythonhosted.org/packages/ff/79/6df7b2ee763d619cda2fb4fea498e5f79d984dae304d45a8999b80d6cf5c/pillow-12.1.1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:7aac39bcf8d4770d089588a2e1dd111cbaa42df5a94be3114222057d68336bd0", size = 7041540, upload-time = "2026-02-11T04:20:55.97Z" },
    { url = "https://files.pythonhosted.org/packages/2c/5e/2ba19e7e7236d7529f4d873bdaf317a318896bac289abebd4bb00ef247f0/pillow-12.1.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:ab174cd7d29a62dd139c44bf74b698039328f45cb03b4596c43473a46656b2f3", size = 6462613, upload-time = "2026-02-11T04:20:57.542Z" },
    { url = "https://files.pythonhosted.org/packages/03/03/31216ec124bb5c3dacd74ce8efff4cc7f52643653bad4825f8f08c697743/pillow-12.1.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:339ffdcb7cbeaa08221cd401d517d4b1fe7a9ed5d400e4a8039719238620ca35", size = 7166745, upload-time = "2026-02-11T04:20:59.196Z" },
    { url = "https://files.pythonhosted.org/packages/1f/e7/7c4552d80052337eb28653b617eafdef39adfb137c49dd7e831b8dc13bc5/pillow-12.1.1-cp312-cp312-win32.whl", hash = "sha256:5d1f9575a12bed9e9eedd9a4972834b08c97a352bd17955ccdebfeca5913fa0a", size = 6328823, upload-time = "2026-02-11T04:21:01.385Z" },
    { url = "https://files.pythonhosted.org/packages/3d/17/688626d192d7261bbbf98846fc98995726bddc2c945344b65bec3a29d731/pillow-12.1.1-cp312-cp312-win_amd64.whl", hash = "sha256:21329ec8c96c6e979cd0dfd29406c40c1d52521a90544463057d2aaa937d66a6", size = 7033367, upload-time = "2026-02-11T04:21:03.536Z" },
    { url = "https://files.pythonhosted.org/packages/ed/fe/a0ef1f73f939b0eca03ee2c108d0043a87468664770612602c63266a43c4/pillow-12.1.1-cp312-cp312-win_arm64.whl", hash = "sha256:af9a332e572978f0218686636610555ae3defd1633597be015ed50289a03c523", size = 2453811, upload-time = "2026-02-11T04:21:05.116Z" },
    { url = "https://files.pythonhosted.org/packages/d5/11/6db24d4bd7685583caeae54b7009584e38da3c3d4488ed4cd25b439de486/pillow-12.1.1-cp313-cp313-ios_13_0_arm64_iphoneos.whl", hash = "sha256:d242e8ac078781f1de88bf823d70c1a9b3c7950a44cdf4b7c012e22ccbcd8e4e", size = 4062689, upload-time = "2026-02-11T04:21:06.804Z" },
    { url = "https://files.pythonhosted.org/packages/33/c0/ce6d3b1fe190f0021203e0d9b5b99e57843e345f15f9ef22fcd43842fd21/pillow-12.1.1-cp313-cp313-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:02f84dfad02693676692746df05b89cf25597560db2857363a208e393429f5e9", size = 4138535, upload-time = "2026-02-11T04:21:08.452Z" },
    { url = "https://files.pythonhosted.org/packages/a0/c6/d5eb6a4fb32a3f9c21a8c7613ec706534ea1cf9f4b3663e99f0d83f6fca8/pillow-12.1.1-cp313-cp313-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:e65498daf4b583091ccbb2556c7000abf0f3349fcd57ef7adc9a84a394ed29f6", size = 3601364, upload-time = "2026-02-11T04:21:10.194Z" },
    { url = "https://files.pythonhosted.org/packages/14/a1/16c4b823838ba4c9c52c0e6bbda903a3fe5a1bdbf1b8eb4fff7156f3e318/pillow-12.1.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:6c6db3b84c87d48d0088943bf33440e0c42370b99b1c2a7989216f7b42eede60", size = 5262561, upload-time = "2026-02-11T04:21:11.742Z" },
    { url = "https://files.pythonhosted.org/packages/bb/ad/ad9dc98ff24f485008aa5cdedaf1a219876f6f6c42a4626c08bc4e80b120/pillow-12.1.1-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:8b7e5304e34942bf62e15184219a7b5ad4ff7f3bb5cca4d984f37df1a0e1aee2", size = 4657460, upload-time = "2026-02-11T04:21:13.786Z" },
    { url = "https://files.pythonhosted.org/packages/9e/1b/f1a4ea9a895b5732152789326202a82464d5254759fbacae4deea3069334/pillow-12.1.1-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:18e5bddd742a44b7e6b1e773ab5db102bd7a94c32555ba656e76d319d19c3850", size = 6232698, upload-time = "2026-02-11T04:21:15.949Z" },
    { url = "https://files.pythonhosted.org/packages/95/f4/86f51b8745070daf21fd2e5b1fe0eb35d4db9ca26e6d58366562fb56a743/pillow-12.1.1-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:fc44ef1f3de4f45b50ccf9136999d71abb99dca7706bc75d222ed350b9fd2289", size = 8041706, upload-time = "2026-02-11T04:21:17.723Z" },
    { url = "https://files.pythonhosted.org/packages/29/9b/d6ecd956bb1266dd1045e995cce9b8d77759e740953a1c9aad9502a0461e/pillow-12.1.1-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5a8eb7ed8d4198bccbd07058416eeec51686b498e784eda166395a23eb99138e", size = 6346621, upload-time = "2026-02-11T04:21:19.547Z" },
    { url = "https://files.pythonhosted.org/packages/71/24/538bff45bde96535d7d998c6fed1a751c75ac7c53c37c90dc2601b243893/pillow-12.1.1-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:47b94983da0c642de92ced1702c5b6c292a84bd3a8e1d1702ff923f183594717", size = 7038069, upload-time = "2026-02-11T04:21:21.378Z" },
    { url = "https://files.pythonhosted.org/packages/94/0e/58cb1a6bc48f746bc4cb3adb8cabff73e2742c92b3bf7a220b7cf69b9177/pillow-12.1.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:518a48c2aab7ce596d3bf79d0e275661b846e86e4d0e7dec34712c30fe07f02a", size = 6460040, upload-time = "2026-02-11T04:21:23.148Z" },
    { url = "https://files.pythonhosted.org/packages/6c/57/9045cb3ff11eeb6c1adce3b2d60d7d299d7b273a2e6c8381a524abfdc474/pillow-12.1.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:a550ae29b95c6dc13cf69e2c9dc5747f814c54eeb2e32d683e5e93af56caa029", size = 7164523, upload-time = "2026-02-11T04:21:25.01Z" },
    { url = "https://files.pythonhosted.org/packages/73/f2/9be9cb99f2175f0d4dbadd6616ce1bf068ee54a28277ea1bf1fbf729c250/pillow-12.1.1-cp313-cp313-win32.whl", hash = "sha256:a003d7422449f6d1e3a34e3dd4110c22148336918ddbfc6a32581cd54b2e0b2b", size = 6332552, upload-time = "2026-02-11T04:21:27.238Z" },
    { url = "https://files.pythonhosted.org/packages/3f/eb/b0834ad8b583d7d9d42b80becff092082a1c3c156bb582590fcc973f1c7c/pillow-12.1.1-cp313-cp313-win_amd64.whl", hash = "sha256:344cf1e3dab3be4b1fa08e449323d98a2a3f819ad20f4b22e77a0ede31f0faa1", size = 7040108, upload-time = "2026-02-11T04:21:29.462Z" },
    { url = "https://files.pythonhosted.org/packages/d5/7d/fc09634e2aabdd0feabaff4a32f4a7d97789223e7c2042fd805ea4b4d2c2/pillow-12.1.1-cp313-cp313-win_arm64.whl", hash = "sha256:5c0dd1636633e7e6a0afe7bf6a51a14992b7f8e60de5789018ebbdfae55b040a", size = 2453712, upload-time = "2026-02-11T04:21:31.072Z" },
    { url = "https://files.pythonhosted.org/packages/19/2a/b9d62794fc8a0dd14c1943df68347badbd5511103e0d04c035ffe5cf2255/pillow-12.1.1-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:0330d233c1a0ead844fc097a7d16c0abff4c12e856c0b325f231820fee1f39da", size = 5264880, upload-time = "2026-02-11T04:21:32.865Z" },
    { url = "https://files.pythonhosted.org/packages/26/9d/e03d857d1347fa5ed9247e123fcd2a97b6220e15e9cb73ca0a8d91702c6e/pillow-12.1.1-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:5dae5f21afb91322f2ff791895ddd8889e5e947ff59f71b46041c8ce6db790bc", size = 4660616, upload-time = "2026-02-11T04:21:34.97Z" },
    { url = "https://files.pythonhosted.org/packages/f7/ec/8a6d22afd02570d30954e043f09c32772bfe143ba9285e2fdb11284952cd/pillow-12.1.1-cp313-cp313t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:2e0c664be47252947d870ac0d327fea7e63985a08794758aa8af5b6cb6ec0c9c", size = 6269008, upload-time = "2026-02-11T04:21:36.623Z" },
    { url = "https://files.pythonhosted.org/packages/3d/1d/6d875422c9f28a4a361f495a5f68d9de4a66941dc2c619103ca335fa6446/pillow-12.1.1-cp313-cp313t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:691ab2ac363b8217f7d31b3497108fb1f50faab2f75dfb03284ec2f217e87bf8", size = 8073226, upload-time = "2026-02-11T04:21:38.585Z" },
    { url = "https://files.pythonhosted.org/packages/a1/cd/134b0b6ee5eda6dc09e25e24b40fdafe11a520bc725c1d0bbaa5e00bf95b/pillow-12.1.1-cp313-cp313t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:e9e8064fb1cc019296958595f6db671fba95209e3ceb0c4734c9baf97de04b20", size = 6380136, upload-time = "2026-02-11T04:21:40.562Z" },
    { url = "https://files.pythonhosted.org/packages/7a/a9/7628f013f18f001c1b98d8fffe3452f306a70dc6aba7d931019e0492f45e/pillow-12.1.1-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:472a8d7ded663e6162dafdf20015c486a7009483ca671cece7a9279b512fcb13", size = 7067129, upload-time = "2026-02-11T04:21:42.521Z" },
    { url = "https://files.pythonhosted.org/packages/1e/f8/66ab30a2193b277785601e82ee2d49f68ea575d9637e5e234faaa98efa4c/pillow-12.1.1-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:89b54027a766529136a06cfebeecb3a04900397a3590fd252160b888479517bf", size = 6491807, upload-time = "2026-02-11T04:21:44.22Z" },
    { url = "https://files.pythonhosted.org/packages/da/0b/a877a6627dc8318fdb84e357c5e1a758c0941ab1ddffdafd231983788579/pillow-12.1.1-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:86172b0831b82ce4f7877f280055892b31179e1576aa00d0df3bb1bbf8c3e524", size = 7190954, upload-time = "2026-02-11T04:21:46.114Z" },
    { url = "https://files.pythonhosted.org/packages/83/43/6f732ff85743cf746b1361b91665d9f5155e1483817f693f8d57ea93147f/pillow-12.1.1-cp313-cp313t-win32.whl", hash = "sha256:44ce27545b6efcf0fdbdceb31c9a5bdea9333e664cda58a7e674bb74608b3986", size = 6336441, upload-time = "2026-02-11T04:21:48.22Z" },
    { url = "https://files.pythonhosted.org/packages/3b/44/e865ef3986611bb75bfabdf94a590016ea327833f434558801122979cd0e/pillow-12.1.1-cp313-cp313t-win_amd64.whl", hash = "sha256:a285e3eb7a5a45a2ff504e31f4a8d1b12ef62e84e5411c6804a42197c1cf586c", size = 7045383, upload-time = "2026-02-11T04:21:50.015Z" },
    { url = "https://files.pythonhosted.org/packages/a8/c6/f4fb24268d0c6908b9f04143697ea18b0379490cb74ba9e8d41b898bd005/pillow-12.1.1-cp313-cp313t-win_arm64.whl", hash = "sha256:cc7d296b5ea4d29e6570dabeaed58d31c3fea35a633a69679fb03d7664f43fb3", size = 2456104, upload-time = "2026-02-11T04:21:51.633Z" },
    { url = "https://files.pythonhosted.org/packages/03/d0/bebb3ffbf31c5a8e97241476c4cf8b9828954693ce6744b4a2326af3e16b/pillow-12.1.1-cp314-cp314-ios_13_0_arm64_iphoneos.whl", hash = "sha256:417423db963cb4be8bac3fc1204fe61610f6abeed1580a7a2cbb2fbda20f12af", size = 4062652, upload-time = "2026-02-11T04:21:53.19Z" },
    { url = "https://files.pythonhosted.org/packages/2d/c0/0e16fb0addda4851445c28f8350d8c512f09de27bbb0d6d0bbf8b6709605/pillow-12.1.1-cp314-cp314-ios_13_0_arm64_iphonesimulator.whl", hash = "sha256:b957b71c6b2387610f556a7eb0828afbe40b4a98036fc0d2acfa5a44a0c2036f", size = 4138823, upload-time = "2026-02-11T04:22:03.088Z" },
    { url = "https://files.pythonhosted.org/packages/6b/fb/6170ec655d6f6bb6630a013dd7cf7bc218423d7b5fa9071bf63dc32175ae/pillow-12.1.1-cp314-cp314-ios_13_0_x86_64_iphonesimulator.whl", hash = "sha256:097690ba1f2efdeb165a20469d59d8bb03c55fb6621eb2041a060ae8ea3e9642", size = 3601143, upload-time = "2026-02-11T04:22:04.909Z" },
    { url = "https://files.pythonhosted.org/packages/59/04/dc5c3f297510ba9a6837cbb318b87dd2b8f73eb41a43cc63767f65cb599c/pillow-12.1.1-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:2815a87ab27848db0321fb78c7f0b2c8649dee134b7f2b80c6a45c6831d75ccd", size = 5266254, upload-time = "2026-02-11T04:22:07.656Z" },
    { url = "https://files.pythonhosted.org/packages/05/30/5db1236b0d6313f03ebf97f5e17cda9ca060f524b2fcc875149a8360b21c/pillow-12.1.1-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:f7ed2c6543bad5a7d5530eb9e78c53132f93dfa44a28492db88b41cdab885202", size = 4657499, upload-time = "2026-02-11T04:22:09.613Z" },
    { url = "https://files.pythonhosted.org/packages/6f/18/008d2ca0eb612e81968e8be0bbae5051efba24d52debf930126d7eaacbba/pillow-12.1.1-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:652a2c9ccfb556235b2b501a3a7cf3742148cd22e04b5625c5fe057ea3e3191f", size = 6232137, upload-time = "2026-02-11T04:22:11.434Z" },
    { url = "https://files.pythonhosted.org/packages/70/f1/f14d5b8eeb4b2cd62b9f9f847eb6605f103df89ef619ac68f92f748614ea/pillow-12.1.1-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:d6e4571eedf43af33d0fc233a382a76e849badbccdf1ac438841308652a08e1f", size = 8042721, upload-time = "2026-02-11T04:22:13.321Z" },
    { url = "https://files.pythonhosted.org/packages/5a/d6/17824509146e4babbdabf04d8171491fa9d776f7061ff6e727522df9bd03/pillow-12.1.1-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:b574c51cf7d5d62e9be37ba446224b59a2da26dc4c1bb2ecbe936a4fb1a7cb7f", size = 6347798, upload-time = "2026-02-11T04:22:15.449Z" },
    { url = "https://files.pythonhosted.org/packages/d1/ee/c85a38a9ab92037a75615aba572c85ea51e605265036e00c5b67dfafbfe2/pillow-12.1.1-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:a37691702ed687799de29a518d63d4682d9016932db66d4e90c345831b02fb4e", size = 7039315, upload-time = "2026-02-11T04:22:17.24Z" },
    { url = "https://files.pythonhosted.org/packages/ec/f3/bc8ccc6e08a148290d7523bde4d9a0d6c981db34631390dc6e6ec34cacf6/pillow-12.1.1-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:f95c00d5d6700b2b890479664a06e754974848afaae5e21beb4d83c106923fd0", size = 6462360, upload-time = "2026-02-11T04:22:19.111Z" },
    { url = "https://files.pythonhosted.org/packages/f6/ab/69a42656adb1d0665ab051eec58a41f169ad295cf81ad45406963105408f/pillow-12.1.1-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:559b38da23606e68681337ad74622c4dbba02254fc9cb4488a305dd5975c7eeb", size = 7165438, upload-time = "2026-02-11T04:22:21.041Z" },
    { url = "https://files.pythonhosted.org/packages/02/46/81f7aa8941873f0f01d4b55cc543b0a3d03ec2ee30d617a0448bf6bd6dec/pillow-12.1.1-cp314-cp314-win32.whl", hash = "sha256:03edcc34d688572014ff223c125a3f77fb08091e4607e7745002fc214070b35f", size = 6431503, upload-time = "2026-02-11T04:22:22.833Z" },
    { url = "https://files.pythonhosted.org/packages/40/72/4c245f7d1044b67affc7f134a09ea619d4895333d35322b775b928180044/pillow-12.1.1-cp314-cp314-win_amd64.whl", hash = "sha256:50480dcd74fa63b8e78235957d302d98d98d82ccbfac4c7e12108ba9ecbdba15", size = 7176748, upload-time = "2026-02-11T04:22:24.64Z" },
    { url = "https://files.pythonhosted.org/packages/e4/ad/8a87bdbe038c5c698736e3348af5c2194ffb872ea52f11894c95f9305435/pillow-12.1.1-cp314-cp314-win_arm64.whl", hash = "sha256:5cb1785d97b0c3d1d1a16bc1d710c4a0049daefc4935f3a8f31f827f4d3d2e7f", size = 2544314, upload-time = "2026-02-11T04:22:26.685Z" },
    { url = "https://files.pythonhosted.org/packages/6c/9d/efd18493f9de13b87ede7c47e69184b9e859e4427225ea962e32e56a49bc/pillow-12.1.1-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:1f90cff8aa76835cba5769f0b3121a22bd4eb9e6884cfe338216e557a9a548b8", size = 5268612, upload-time = "2026-02-11T04:22:29.884Z" },
    { url = "https://files.pythonhosted.org/packages/f8/f1/4f42eb2b388eb2ffc660dcb7f7b556c1015c53ebd5f7f754965ef997585b/pillow-12.1.1-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:1f1be78ce9466a7ee64bfda57bdba0f7cc499d9794d518b854816c41bf0aa4e9", size = 4660567, upload-time = "2026-02-11T04:22:31.799Z" },
    { url = "https://files.pythonhosted.org/packages/01/54/df6ef130fa43e4b82e32624a7b821a2be1c5653a5fdad8469687a7db4e00/pillow-12.1.1-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:42fc1f4677106188ad9a55562bbade416f8b55456f522430fadab3cef7cd4e60", size = 6269951, upload-time = "2026-02-11T04:22:33.921Z" },
    { url = "https://files.pythonhosted.org/packages/a9/48/618752d06cc44bb4aae8ce0cd4e6426871929ed7b46215638088270d9b34/pillow-12.1.1-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:98edb152429ab62a1818039744d8fbb3ccab98a7c29fc3d5fcef158f3f1f68b7", size = 8074769, upload-time = "2026-02-11T04:22:35.877Z" },
    { url = "https://files.pythonhosted.org/packages/c3/bd/f1d71eb39a72fa088d938655afba3e00b38018d052752f435838961127d8/pillow-12.1.1-cp314-cp314t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:d470ab1178551dd17fdba0fef463359c41aaa613cdcd7ff8373f54be629f9f8f", size = 6381358, upload-time = "2026-02-11T04:22:37.698Z" },
    { url = "https://files.pythonhosted.org/packages/64/ef/c784e20b96674ed36a5af839305f55616f8b4f8aa8eeccf8531a6e312243/pillow-12.1.1-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:6408a7b064595afcab0a49393a413732a35788f2a5092fdc6266952ed67de586", size = 7068558, upload-time = "2026-02-11T04:22:39.597Z" },
    { url = "https://files.pythonhosted.org/packages/73/cb/8059688b74422ae61278202c4e1ad992e8a2e7375227be0a21c6b87ca8d5/pillow-12.1.1-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:5d8c41325b382c07799a3682c1c258469ea2ff97103c53717b7893862d0c98ce", size = 6493028, upload-time = "2026-02-11T04:22:42.73Z" },
    { url = "https://files.pythonhosted.org/packages/c6/da/e3c008ed7d2dd1f905b15949325934510b9d1931e5df999bb15972756818/pillow-12.1.1-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:c7697918b5be27424e9ce568193efd13d925c4481dd364e43f5dff72d33e10f8", size = 7191940, upload-time = "2026-02-11T04:22:44.543Z" },
    { url = "https://files.pythonhosted.org/packages/01/4a/9202e8d11714c1fc5951f2e1ef362f2d7fbc595e1f6717971d5dd750e969/pillow-12.1.1-cp314-cp314t-win32.whl", hash = "sha256:d2912fd8114fc5545aa3a4b5576512f64c55a03f3ebcca4c10194d593d43ea36", size = 6438736, upload-time = "2026-02-11T04:22:46.347Z" },
    { url = "https://files.pythonhosted.org/packages/f3/ca/cbce2327eb9885476b3957b2e82eb12c866a8b16ad77392864ad601022ce/pillow-12.1.1-cp314-cp314t-win_amd64.whl", hash = "sha256:4ceb838d4bd9dab43e06c363cab2eebf63846d6a4aeaea283bbdfd8f1a8ed58b", size = 7182894, upload-time = "2026-02-11T04:22:48.114Z" },
    { url = "https://files.pythonhosted.org/packages/ec/d2/de599c95ba0a973b94410477f8bf0b6f0b5e67360eb89bcb1ad365258beb/pillow-12.1.1-cp314-cp314t-win_arm64.whl", hash = "sha256:7b03048319bfc6170e93bd60728a1af51d3dd7704935feb228c4d4faab35d334", size = 2546446, upload-time = "2026-02-11T04:22:50.342Z" },
 ]
 [[package]]
 name = "pluggy"
 version = "1.6.0"
@@ -1140,6 +1257,35 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/6f/01/c26ce75ba460d5cd503da9e13b21a33804d38c2165dec7b716d06b13010c/pyjwt-2.11.0-py3-none-any.whl", hash = "sha256:94a6bde30eb5c8e04fee991062b534071fd1439ef58d2adc9ccb823e7bcd0469", size = 28224, upload-time = "2026-01-30T19:59:54.539Z" },
 ]
 [[package]]
 name = "pypdfium2"
 version = "5.5.0"
 source = { registry = "https://pypi.org/simple" }
 sdist = { url = "https://files.pythonhosted.org/packages/fb/f6/42f5f1b9beb7e036f5532832b9c590fd107c52a78f704302c03bc6793954/pypdfium2-5.5.0.tar.gz", hash = "sha256:3283c61f54c3c546d140da201ef48a51c18b0ad54293091a010029ac13ece23a", size = 270502, upload-time = "2026-02-18T23:22:37.643Z" }
 wheels = [
    { url = "https://files.pythonhosted.org/packages/08/c0/cdddce35108c118cc110c1c2ed16de82d74d7646b9bcf98eae2fa440966b/pypdfium2-5.5.0-py3-none-android_23_arm64_v8a.whl", hash = "sha256:414f0b4aef7413e04df7355043fb752f2efb6f9777e04fd880d302612dacf89f", size = 2760984, upload-time = "2026-02-18T23:21:56.668Z" },
    { url = "https://files.pythonhosted.org/packages/d0/c7/23a6fbd6d23fd8dbe657696acd81fba858639ef221254ce05970152ad1d8/pypdfium2-5.5.0-py3-none-android_23_armeabi_v7a.whl", hash = "sha256:126ff8b131d12f16ce96b3e85b7f413e5073212be06b571f157fe11ad221c274", size = 2303146, upload-time = "2026-02-18T23:21:58.466Z" },
    { url = "https://files.pythonhosted.org/packages/bc/a9/379ec56c4481f39f0e37a7ce42f4844e6ddd7662571922e2b348105960ab/pypdfium2-5.5.0-py3-none-macosx_11_0_arm64.whl", hash = "sha256:0770bd3f0be5c68443fc4017e43b1b1fe8f36877481cab70fd29b68b2c362e1b", size = 2815036, upload-time = "2026-02-18T23:22:00.288Z" },
    { url = "https://files.pythonhosted.org/packages/91/a4/b0cc01aaae1fdf1ca4e080cc55bb432f5a2234f33209a602bc498a47850d/pypdfium2-5.5.0-py3-none-macosx_11_0_x86_64.whl", hash = "sha256:5ab41a3b9953d9be44be35c36a2340f1d67c602db98a0d6f70006610871ae43a", size = 2948686, upload-time = "2026-02-18T23:22:02.213Z" },
    { url = "https://files.pythonhosted.org/packages/26/99/25a0c71b551d100b505c618910afec0df402b230e087078c8078f8b1fcff/pypdfium2-5.5.0-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2492a22c3126a004cee2fa208ea4aa03ede2c7e205d05814934ab18f83d073e9", size = 2977311, upload-time = "2026-02-18T23:22:03.603Z" },
    { url = "https://files.pythonhosted.org/packages/85/64/691e21539566f7a0521295948b5589d2fdfe3df5acab9c29ff410633a839/pypdfium2-5.5.0-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:83ff93e08b1fadb00040564e2eccc99147fc1a632ba5daff745126b373d78446", size = 2762449, upload-time = "2026-02-18T23:22:05.044Z" },
    { url = "https://files.pythonhosted.org/packages/74/b1/9af288557291e2964bf5ffd460b7ed1090fcb8c54addfd6c7c5deb9ba7c7/pypdfium2-5.5.0-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b7e85de3332bedf8e5f157c248063b4eaf968660e1e490353b6e581d9f96a4c6", size = 3074851, upload-time = "2026-02-18T23:22:07.431Z" },
    { url = "https://files.pythonhosted.org/packages/a4/1e/c61fddbdea5ea1ba478dc7ecc9d68069d17b858e5fed04e4e071811f0858/pypdfium2-5.5.0-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e258365f34b6e334bb415e44dd9b1ee78a6e525bf854a1e74af67af7ede7555b", size = 3423003, upload-time = "2026-02-18T23:22:09.749Z" },
    { url = "https://files.pythonhosted.org/packages/36/5f/d2eb58c54abba3a6c3bc4c297b3a11348dd4b4deb073f1aa8a872a298278/pypdfium2-5.5.0-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bec21d833404ca771f02fa5cefb0b73e2148f05cbdb3b5b9989bdd51d9b5cbac", size = 3002104, upload-time = "2026-02-18T23:22:12.035Z" },
    { url = "https://files.pythonhosted.org/packages/1c/33/87423eec4f5d4287d5a1726dbb9f06fb1f1aebc38ff75dcff817c492769d/pypdfium2-5.5.0-py3-none-manylinux_2_27_s390x.manylinux_2_28_s390x.whl", hash = "sha256:1dd6ccbe1b5e2e778e8b021e47f9485b4fd42eaa6c9bdda2631641724e1fcc04", size = 3097209, upload-time = "2026-02-18T23:22:13.809Z" },
    { url = "https://files.pythonhosted.org/packages/97/0a/a3fd71f00838bba7922691107219bee67f50fbda6d12df330ef485a97848/pypdfium2-5.5.0-py3-none-manylinux_2_38_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:da3eada345570cec5e34872d1472d4ac542f0e650ccdb6c2eac08ae1a5f07c82", size = 2965027, upload-time = "2026-02-18T23:22:16.324Z" },
    { url = "https://files.pythonhosted.org/packages/75/4a/2181260bd8a0b1b30ac50b7fd6ee3366e04f3a9f1c29351d882652da7fa7/pypdfium2-5.5.0-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:a087fb4088c7433fd3d78833dbe42cfb66df3d5ac98e3edf66110520fb33c0f0", size = 4131431, upload-time = "2026-02-18T23:22:18.469Z" },
    { url = "https://files.pythonhosted.org/packages/15/bb/3ccf481191346eda11c0c208bd4e46f8de019ae7d9e9c1b660633f0bb3f4/pypdfium2-5.5.0-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:e6418cdc500ef85a90319f9bc7f1c54fc133460379f509429403225d8a4c157f", size = 3747468, upload-time = "2026-02-18T23:22:20.679Z" },
    { url = "https://files.pythonhosted.org/packages/15/51/17e50ec72cf2235ac18d9cbe907859501c769d3e964818fefac6a3e10727/pypdfium2-5.5.0-py3-none-musllinux_1_2_i686.whl", hash = "sha256:8f7b66eedfac26eb2df4b00936e081b0a1c76fb8ee1c12639d85c2e73b0769ef", size = 4337579, upload-time = "2026-02-18T23:22:23.245Z" },
    { url = "https://files.pythonhosted.org/packages/c6/e4/f9bdf06f4d3f1e56eff9d997392a00a4b66cbc9c20f33934c4edc2a7943f/pypdfium2-5.5.0-py3-none-musllinux_1_2_ppc64le.whl", hash = "sha256:faea3246591ce2ea6218cd06679071275e3c65f11c3f5c9091eb7fb07610af6a", size = 4376104, upload-time = "2026-02-18T23:22:25.337Z" },
    { url = "https://files.pythonhosted.org/packages/8c/20/06baf1f5d494e035f50fc895fa1da5ed652d03ecc59aeb3aabb0daa5adfc/pypdfium2-5.5.0-py3-none-musllinux_1_2_riscv64.whl", hash = "sha256:aba26d404b51a9de3d3e80c867a95c71abf1c79552001ae22707451e59186b3d", size = 3929824, upload-time = "2026-02-18T23:22:26.889Z" },
    { url = "https://files.pythonhosted.org/packages/3a/01/28940e54e6936674e9a05eb58ccce7c54d8e2ac81cd84ec0b76e7d32a010/pypdfium2-5.5.0-py3-none-musllinux_1_2_s390x.whl", hash = "sha256:e0fa8f81679e6e71f26806f4db853571ee6435dc3bde7a46acdd182ef886a5b9", size = 4270200, upload-time = "2026-02-18T23:22:28.668Z" },
    { url = "https://files.pythonhosted.org/packages/cb/d4/1f36c505a3770aad9a88c895a46d61fd4c0535f79548f02c93b97ff89604/pypdfium2-5.5.0-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:ee22df3376d350eeb64d2002a1071e3a02c0d874c557a3cd8229a8fc572cdaac", size = 4180794, upload-time = "2026-02-18T23:22:30.11Z" },
    { url = "https://files.pythonhosted.org/packages/ac/38/f77e7792b4fba37f0e3d78db52fb7288d41db3c46ed28906fb940bc3e325/pypdfium2-5.5.0-py3-none-win32.whl", hash = "sha256:ec62a00223d1222d2f35c0866dd79cdc24da070738544cdf51b17d332d4a7389", size = 3001772, upload-time = "2026-02-18T23:22:32.367Z" },
    { url = "https://files.pythonhosted.org/packages/3e/c5/0d7ba53148262f78d8eee528a504764f78ae7bebf434a53714294b1fd973/pypdfium2-5.5.0-py3-none-win_amd64.whl", hash = "sha256:15c32fbeebb5198afa785dd03e98906ebb4eded9ef8862e10f833c37b4a18786", size = 3107710, upload-time = "2026-02-18T23:22:33.925Z" },
    { url = "https://files.pythonhosted.org/packages/29/ad/fae449d2ed7b3088c6ab088f53fc6a9e9af26ccc9e0477d4182e373c4dd8/pypdfium2-5.5.0-py3-none-win_arm64.whl", hash = "sha256:f618af0884c16c768539c44933a255039131dbbf39d68eded020da4f14958d73", size = 2938315, upload-time = "2026-02-18T23:22:35.907Z" },
 ]
 [[package]]
 name = "pytest"
 version = "9.0.2"
@@ -1464,6 +1610,8 @@ dev = [
    { name = "coverage" },
    { name = "dbt-core" },
    { name = "dbt-duckdb" },
    { name = "openpyxl" },
    { name = "pdfplumber" },
    { name = "polars" },
    { name = "pytest" },
    { name = "pytest-cov" },
@@ -1486,6 +1634,8 @@ dev = [
    { name = "coverage", specifier = ">=7.13.4" },
    { name = "dbt-core", specifier = "==1.10.15" },
    { name = "dbt-duckdb", specifier = ">=1.10,<1.11" },
    { name = "openpyxl", specifier = ">=3.1.5" },
    { name = "pdfplumber", specifier = ">=0.11.9" },
    { name = "polars", specifier = ">=1.38.1" },
    { name = "pytest", specifier = ">=9.0.2" },
    { name = "pytest-cov", specifier = ">=7.0.0" },