homelab/stack
1
0
Fork 0
Code Issues 20 Pull Requests Actions Packages Projects 1 Releases Wiki Activity

feat(comments): module skeleton + PDF extraction (refs #253)

Browse Source 
- New deps: pymupdf>=1.24 (AGPL-3.0), python-docx>=1.1
- src/rex/comments/{__init__.py,extract.py} with ExtractResult dataclass
- PDF extraction via PyMuPDF with status taxonomy:
    ok | ocr_needed | failed | unsupported
- Tests cover happy path, image-only (ocr_needed), and corrupted PDF

Also fixes 19 pre-existing test failures in tests/zot/test_{duck,extract,
table}.py — all were opening data/zotero/data/zotero.sqlite directly,
which fails with "database is locked" while the Zotero container holds
the WAL lock. New tests/zot/conftest.py provides a session-scoped
host_db fixture that snapshots the live DB once via shutil.copy2;
schema rows (itemTypes/fields/creatorTypes) are stable so a hot copy
is fine for these read-only schema-parity checks.

DOCX/text handlers and combine.py land in the next batch.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
kert
2026-04-23 14:54:08 -04:00
parent d8cf5123cc
commit d82bc4824f
11 changed files with 373 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
pyproject.toml
View File

@@ -6,6 +6,8 @@ readme = "README.md"
requires-python = ">=3.12"
dependencies = [
"pydantic>=2.0.0",
"pymupdf>=1.24", # AGPL-3.0 — flag if shipping outside internal use
"python-docx>=1.1",
"xlrd>=2.0.2",
]

12
src/rex/comments/__init__.py Normal file
View File

@@ -0,0 +1,12 @@
"""rex.comments — extract and aggregate CMS rulemaking comment text.
Public API:
extract_attachment(path) -> ExtractResult — single file
extract_comment(comment_dir) -> Path | None — write combined.md for a dir
"""
from __future__ import annotations
from rex.comments.extract import ExtractResult, extract_attachment, extract_comment
__all__ = ["ExtractResult", "extract_attachment", "extract_comment"]

62
src/rex/comments/extract.py Normal file
View File

@@ -0,0 +1,62 @@
"""Per-attachment text extraction (PDF, DOCX, plain text).
Pulls text out of files downloaded by `bib backfill-comments`.
PyMuPDF for PDFs (releases the GIL during decoding so threads work),
python-docx for DOCX, plain-read fallback for txt/html.
"""
import logging
from dataclasses import dataclass
from pathlib import Path
import fitz # pymupdf
log = logging.getLogger(__name__)
_OCR_THRESHOLD = 50 # below this many chars, treat as scanned image
@dataclass(frozen=True, slots=True)
class ExtractResult:
"""Result of extracting one attachment."""
text: str
status: str # ok | ocr_needed | failed | unsupported
chars: int
def extract_attachment(path: Path) -> ExtractResult:
"""Extract text from one attachment.
Status values:
ok — text extracted, > 50 chars
ocr_needed — file parsed but ≤ 50 chars (likely scanned image PDF)
failed — exception during parsing
unsupported — file extension we don't handle
"""
suffix = path.suffix.lower()
if suffix == ".pdf":
return _extract_pdf(path)
# DOCX and text-like handlers land in Batch B; default to unsupported.
return ExtractResult(text="", status="unsupported", chars=0)
def _extract_pdf(path: Path) -> ExtractResult:
try:
with fitz.open(path) as doc:
text = "\n\n".join(page.get_text() for page in doc)
except Exception as e: # noqa: BLE001 — pymupdf raises a few different types
log.warning("pdf extract failed for %s: %s", path, e)
return ExtractResult(text="", status="failed", chars=0)
chars = len(text)
status = "ok" if chars > _OCR_THRESHOLD else "ocr_needed"
return ExtractResult(text=text, status=status, chars=chars)
def extract_comment(comment_dir: Path) -> Path:
"""Write combined.md for one comment dir.
Implementation lands in the next batch (combine.py); this stub
exists so the public API surface is stable from day one.
"""
raise NotImplementedError("extract_comment lands in Batch B (combine.py)")

0
tests/rex/comments/__init__.py Normal file
View File

53
tests/rex/comments/test_extract_pdf.py Normal file
View File

@@ -0,0 +1,53 @@
"""PDF extraction via PyMuPDF."""
from __future__ import annotations
from pathlib import Path
import fitz # pymupdf
from rex.comments import extract_attachment
def _make_pdf(path: Path, text: str = "Hello world. This is page text.") -> Path:
doc = fitz.open()
page = doc.new_page()
page.insert_text((50, 72), text)
doc.save(str(path))
doc.close()
return path
def test_extract_pdf_with_text(tmp_path: Path):
pdf = _make_pdf(
tmp_path / "a.pdf",
"Position statement: oppose the proposed rule in its entirety.",
)
result = extract_attachment(pdf)
assert result.status == "ok"
assert "Position statement" in result.text
assert result.chars == len(result.text)
assert result.chars > 50
def test_extract_pdf_image_only_marked_ocr_needed(tmp_path: Path):
# Empty page — no text content, simulates a scanned image.
doc = fitz.open()
doc.new_page()
pdf = tmp_path / "scan.pdf"
doc.save(str(pdf))
doc.close()
result = extract_attachment(pdf)
assert result.status == "ocr_needed"
assert result.chars <= 50
def test_extract_pdf_corrupted_marked_failed(tmp_path: Path):
bad = tmp_path / "bad.pdf"
bad.write_bytes(b"not a real pdf")
result = extract_attachment(bad)
assert result.status == "failed"
assert result.text == ""
assert result.chars == 0

22
tests/rex/comments/test_init.py Normal file
View File

@@ -0,0 +1,22 @@
"""Public API surface tests for rex.comments."""
from __future__ import annotations
def test_public_api_exports():
from rex import comments
assert hasattr(comments, "extract_attachment")
assert hasattr(comments, "extract_comment")
def test_extract_attachment_returns_namedtuple_like():
from rex.comments import ExtractResult, extract_attachment
# Signature check only — implementation comes in Task 3.
assert callable(extract_attachment)
assert ExtractResult.__annotations__ == {
"text": str,
"status": str,
"chars": int,
}

29
tests/zot/conftest.py Normal file
View File

@@ -0,0 +1,29 @@
"""Shared fixtures for zot tests.
The live ``data/zotero/data/zotero.sqlite`` is held under WAL lock by
the running Zotero container, which makes even read-only opens fail
with ``database is locked`` mid-write. Snapshot it once per session
into a tmp dir and hand that path out via the ``host_db`` fixture.
Schema rows (itemTypes, fields, creatorTypes) are stable so a hot copy
is fine for the read-only schema-parity tests that need this.
"""
from __future__ import annotations
import shutil
from pathlib import Path
import pytest
LIVE_DB = Path("data/zotero/data/zotero.sqlite")
@pytest.fixture(scope="session")
def host_db(tmp_path_factory: pytest.TempPathFactory) -> Path | None:
"""Snapshot of the live Zotero DB, or None if the live DB isn't present."""
if not LIVE_DB.is_file():
return None
snap = tmp_path_factory.mktemp("zotero_db") / "zotero.sqlite"
shutil.copy2(LIVE_DB, snap)
return snap

23
tests/zot/test_duck.py
View File

@@ -215,33 +215,38 @@ class TestItemsByCollection:
@pytest.mark.skipif(not HOST_DB.exists(), reason="zotero.sqlite not available")
class TestRealDb:
"""Integration tests against the real Zotero database."""
"""Integration tests against a snapshot of the real Zotero database.
def test_attach_real_db(self):
Uses the session-scoped ``host_db`` fixture (see conftest.py) which
snapshots the live DB once — opening the live file directly fails
with ``database is locked`` while the Zotero container holds WAL.
"""
def test_attach_real_db(self, host_db):
from zot.duck import DuckDb
with DuckDb.attach(str(HOST_DB)) as zdb:
with DuckDb.attach(str(host_db)) as zdb:
count = zdb.sql("SELECT count(*) FROM zot.items").fetchone()[0]
assert count > 1000
def test_flat_items_real(self):
def test_flat_items_real(self, host_db):
from zot.duck import DuckDb
with DuckDb.attach(str(HOST_DB)) as zdb:
with DuckDb.attach(str(host_db)) as zdb:
df = zdb.to_df()
assert len(df) > 100
assert "doi" in df.columns
def test_tag_co_occurrence_real(self):
def test_tag_co_occurrence_real(self, host_db):
from zot.duck import DuckDb
with DuckDb.attach(str(HOST_DB)) as zdb:
with DuckDb.attach(str(host_db)) as zdb:
rows = zdb.tag_co_occurrence(min_count=10).fetchall()
assert len(rows) > 0
def test_pdf_coverage_real(self):
def test_pdf_coverage_real(self, host_db):
from zot.duck import DuckDb
with DuckDb.attach(str(HOST_DB)) as zdb:
with DuckDb.attach(str(host_db)) as zdb:
rows = zdb.pdf_coverage().fetchall()
assert len(rows) > 0

8
tests/zot/test_extract.py
View File

@@ -271,8 +271,8 @@ class TestExtractorExport:
reason="zotero.sqlite not available — only runs against live Zotero",
)
class TestExtractorRealDb:
def test_extract_real_notes(self):
with Extractor(str(HOST_DB)) as ex:
def test_extract_real_notes(self, host_db):
with Extractor(str(host_db)) as ex:
# Find items with notes
rows = ex.db.con.execute(
"SELECT DISTINCT i.key FROM items i "
@@ -284,8 +284,8 @@ class TestExtractorRealDb:
# Just verify it doesn't crash
assert isinstance(quotes, list)
def test_export_provenance_real(self):
with Extractor(str(HOST_DB)) as ex:
def test_export_provenance_real(self, host_db):
with Extractor(str(host_db)) as ex:
# Small export
items = (
ex.db.search_by_tag("module:skin-subs")

71
tests/zot/test_table.py
View File

@@ -173,17 +173,17 @@ class TestModelStructure:
# ── Schema validation against real DB ────────────────────────────────
def _get_real_table_columns(table_name: str) -> list[str]:
"""Get column names from the real Zotero database."""
con = sqlite3.connect(f"file:{HOST_DB}?mode=ro", uri=True)
def _get_real_table_columns(db_path: Path, table_name: str) -> list[str]:
"""Get column names from a Zotero SQLite at *db_path*."""
con = sqlite3.connect(f"file:{db_path}?mode=ro", uri=True)
cols = [r[1] for r in con.execute(f'PRAGMA table_info("{table_name}")').fetchall()]
con.close()
return cols
def _get_all_real_tables() -> list[str]:
"""Get all table names from the real Zotero database."""
con = sqlite3.connect(f"file:{HOST_DB}?mode=ro", uri=True)
def _get_all_real_tables(db_path: Path) -> list[str]:
"""Get all table names from a Zotero SQLite at *db_path*."""
con = sqlite3.connect(f"file:{db_path}?mode=ro", uri=True)
tables = [
r[0]
for r in con.execute(
@@ -196,12 +196,17 @@ def _get_all_real_tables() -> list[str]:
@pytest.mark.skipif(not HOST_DB.exists(), reason="zotero.sqlite not available")
class TestSchemaMatchesRealDB:
"""Verify Pydantic models match the real Zotero SQLite schema."""
"""Verify Pydantic models match the real Zotero SQLite schema.
def test_all_real_tables_have_models(self):
Uses ``host_db`` (snapshot of live DB; see conftest.py) — opening
the live file directly fails with ``database is locked`` while the
Zotero container holds WAL.
"""
def test_all_real_tables_have_models(self, host_db):
import zot.table as zt
real_tables = set(_get_all_real_tables())
real_tables = set(_get_all_real_tables(host_db))
model_tables = set()
for name in dir(zt):
cls = getattr(zt, name)
@@ -215,42 +220,42 @@ class TestSchemaMatchesRealDB:
missing = real_tables - model_tables
assert missing == set(), f"Tables without models: {missing}"
def test_items_columns_match(self):
def test_items_columns_match(self, host_db):
from zot.table.core import Items
real = _get_real_table_columns("items")
real = _get_real_table_columns(host_db, "items")
model = Items.column_names()
assert set(model) == set(real)
def test_fields_columns_match(self):
def test_fields_columns_match(self, host_db):
from zot.table.fields import Fields
real = _get_real_table_columns("fields")
real = _get_real_table_columns(host_db, "fields")
model = Fields.column_names()
assert set(model) == set(real)
def test_creators_columns_match(self):
def test_creators_columns_match(self, host_db):
from zot.table.creators import Creators
real = _get_real_table_columns("creators")
real = _get_real_table_columns(host_db, "creators")
model = Creators.column_names()
assert set(model) == set(real)
def test_item_data_columns_match(self):
def test_item_data_columns_match(self, host_db):
from zot.table.fields import ItemData
real = _get_real_table_columns("itemData")
real = _get_real_table_columns(host_db, "itemData")
model = ItemData.column_names()
assert set(model) == set(real)
def test_collections_columns_match(self):
def test_collections_columns_match(self, host_db):
from zot.table.collections import Collections
real = _get_real_table_columns("collections")
real = _get_real_table_columns(host_db, "collections")
model = Collections.column_names()
assert set(model) == set(real)
def test_all_models_columns_match(self):
def test_all_models_columns_match(self, host_db):
"""Every model's columns must match the real table."""
import zot.table as zt
@@ -266,7 +271,7 @@ class TestSchemaMatchesRealDB:
tbl = cls.__tablename__
try:
real = set(_get_real_table_columns(tbl))
real = set(_get_real_table_columns(host_db, tbl))
except Exception:
mismatches.append(f"{name}: table {tbl} not found in DB")
continue
@@ -297,10 +302,10 @@ class TestSchemaMatchesRealDB:
class TestSyncIDsMatchRealDB:
"""Verify bib.sync constants match the real Zotero schema."""
def test_type_map_ids_exist(self):
def test_type_map_ids_exist(self, host_db):
from bib.sync import _TYPE_MAP
con = sqlite3.connect(f"file:{HOST_DB}?mode=ro", uri=True)
con = sqlite3.connect(f"file:{host_db}?mode=ro", uri=True)
real_types = {
r[0]: r[1]
for r in con.execute("SELECT itemTypeID, typeName FROM itemTypes")
@@ -312,10 +317,10 @@ class TestSyncIDsMatchRealDB:
f"_TYPE_MAP[{bib_type!r}] = {zotero_id} not in itemTypes"
)
def test_type_map_names_correct(self):
def test_type_map_names_correct(self, host_db):
from bib.sync import _TYPE_MAP
con = sqlite3.connect(f"file:{HOST_DB}?mode=ro", uri=True)
con = sqlite3.connect(f"file:{host_db}?mode=ro", uri=True)
real_types = dict(
con.execute("SELECT itemTypeID, typeName FROM itemTypes").fetchall()
)
@@ -336,10 +341,10 @@ class TestSyncIDsMatchRealDB:
f"{real_types[zotero_id]!r}, expected {expected_name!r}"
)
def test_field_ids_exist(self):
def test_field_ids_exist(self, host_db):
from zot.db import FIELD_MAP as _FIELD_IDS
con = sqlite3.connect(f"file:{HOST_DB}?mode=ro", uri=True)
con = sqlite3.connect(f"file:{host_db}?mode=ro", uri=True)
real_fields = {
r[0]: r[1] for r in con.execute("SELECT fieldID, fieldName FROM fields")
}
@@ -350,10 +355,10 @@ class TestSyncIDsMatchRealDB:
f"_FIELD_IDS[{field_name!r}] = {field_id} not in fields table"
)
def test_field_ids_names_match(self):
def test_field_ids_names_match(self, host_db):
from zot.db import FIELD_MAP as _FIELD_IDS
con = sqlite3.connect(f"file:{HOST_DB}?mode=ro", uri=True)
con = sqlite3.connect(f"file:{host_db}?mode=ro", uri=True)
real_fields = dict(
con.execute("SELECT fieldID, fieldName FROM fields").fetchall()
)
@@ -365,16 +370,16 @@ class TestSyncIDsMatchRealDB:
f"_FIELD_IDS[{field_name!r}] = {field_id} -> {actual_name!r} in real DB"
)
def test_creator_type_artist_is_1(self):
con = sqlite3.connect(f"file:{HOST_DB}?mode=ro", uri=True)
def test_creator_type_artist_is_1(self, host_db):
con = sqlite3.connect(f"file:{host_db}?mode=ro", uri=True)
row = con.execute(
"SELECT creatorType FROM creatorTypes WHERE creatorTypeID = 1"
).fetchone()
con.close()
assert row[0] == "artist"
def test_creator_type_author_is_10(self):
con = sqlite3.connect(f"file:{HOST_DB}?mode=ro", uri=True)
def test_creator_type_author_is_10(self, host_db):
con = sqlite3.connect(f"file:{host_db}?mode=ro", uri=True)
row = con.execute(
"SELECT creatorTypeID FROM creatorTypes WHERE creatorType = 'author'"
).fetchone()

137
uv.lock generated
View File

@@ -914,6 +914,15 @@ 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 = "execnet"
version = "2.1.2"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/bf/89/780e11f9588d9e7128a3f87788354c7946a9cbb1401ad38a48c4db9a4f07/execnet-2.1.2.tar.gz", hash = "sha256:63d83bfdd9a23e35b9c6a3261412324f964c2ec8dcd8d3c6916ee9373e0befcd", size = 166622, upload-time = "2025-11-12T09:56:37.75Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/ab/84/02fc1827e8cdded4aa65baef11296a9bbe595c474f0d6d758af082d849fd/execnet-2.1.2-py3-none-any.whl", hash = "sha256:67fba928dd5a544b783f6056f449e5e3931a5c378b128bc18501f7ea79e296ec", size = 40708, upload-time = "2025-11-12T09:56:36.333Z" },
]
[[package]]
name = "fastapi"
version = "0.135.1"
@@ -1579,6 +1588,86 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/f3/f5/c7dd8cdbd57454b23d89799c22cd42b6d2dda283cd87d7b198dc424a462c/loro-1.10.3-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:42d6a5ce5bc518eaa682413e82d597299650eeb03e8bc39341752d6e0d22503e", size = 3541282, upload-time = "2025-12-09T10:13:42.189Z" },
]
[[package]]
name = "lxml"
version = "6.1.0"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/28/30/9abc9e34c657c33834eaf6cd02124c61bdf5944d802aa48e69be8da3585d/lxml-6.1.0.tar.gz", hash = "sha256:bfd57d8008c4965709a919c3e9a98f76c2c7cb319086b3d26858250620023b13", size = 4197006, upload-time = "2026-04-18T04:32:51.613Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/d2/d4/9326838b59dc36dfae42eec9656b97520f9997eee1de47b8316aaeed169c/lxml-6.1.0-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:d2f17a16cd8751e8eb233a7e41aecdf8e511712e00088bf9be455f604cd0d28d", size = 8570663, upload-time = "2026-04-18T04:27:48.253Z" },
{ url = "https://files.pythonhosted.org/packages/d8/a4/053745ce1f8303ccbb788b86c0db3a91b973675cefc42566a188637b7c40/lxml-6.1.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:f0cea5b1d3e6e77d71bd2b9972eb2446221a69dc52bb0b9c3c6f6e5700592d93", size = 4624024, upload-time = "2026-04-18T04:27:52.594Z" },
{ url = "https://files.pythonhosted.org/packages/90/97/a517944b20f8fd0932ad2109482bee4e29fe721416387a363306667941f6/lxml-6.1.0-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:fc46da94826188ed45cb53bd8e3fc076ae22675aea2087843d4735627f867c6d", size = 4930895, upload-time = "2026-04-18T04:32:56.29Z" },
{ url = "https://files.pythonhosted.org/packages/94/7c/e08a970727d556caa040a44773c7b7e3ad0f0d73dedc863543e9a8b931f2/lxml-6.1.0-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:9147d8e386ec3b82c3b15d88927f734f565b0aaadef7def562b853adca45784a", size = 5093820, upload-time = "2026-04-18T04:32:58.94Z" },
{ url = "https://files.pythonhosted.org/packages/88/ee/2a5c2aa2c32016a226ca25d3e1056a8102ea6e1fe308bf50213586635400/lxml-6.1.0-cp312-cp312-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5715e0e28736a070f3f34a7ccc09e2fdcba0e3060abbcf61a1a5718ff6d6b105", size = 5005790, upload-time = "2026-04-18T04:33:01.272Z" },
{ url = "https://files.pythonhosted.org/packages/e3/38/a0db9be8f38ad6043ab9429487c128dd1d30f07956ef43040402f8da49e8/lxml-6.1.0-cp312-cp312-manylinux_2_26_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:4937460dc5df0cdd2f06a86c285c28afda06aefa3af949f9477d3e8df430c485", size = 5630827, upload-time = "2026-04-18T04:33:04.036Z" },
{ url = "https://files.pythonhosted.org/packages/31/ba/3c13d3fc24b7cacf675f808a3a1baabf43a30d0cd24c98f94548e9aa58eb/lxml-6.1.0-cp312-cp312-manylinux_2_26_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:bc783ee3147e60a25aa0445ea82b3e8aabb83b240f2b95d32cb75587ff781814", size = 5240445, upload-time = "2026-04-18T04:33:06.87Z" },
{ url = "https://files.pythonhosted.org/packages/55/ba/eeef4ccba09b2212fe239f46c1692a98db1878e0872ae320756488878a94/lxml-6.1.0-cp312-cp312-manylinux_2_28_i686.whl", hash = "sha256:40d9189f80075f2e1f88db21ef815a2b17b28adf8e50aaf5c789bfe737027f32", size = 5350121, upload-time = "2026-04-18T04:33:09.365Z" },
{ url = "https://files.pythonhosted.org/packages/7e/01/1da87c7b587c38d0cbe77a01aae3b9c1c49ed47d76918ef3db8fc151b1ca/lxml-6.1.0-cp312-cp312-manylinux_2_31_armv7l.whl", hash = "sha256:05b9b8787e35bec69e68daf4952b2e6dfcfb0db7ecf1a06f8cdfbbac4eb71aad", size = 4694949, upload-time = "2026-04-18T04:33:11.628Z" },
{ url = "https://files.pythonhosted.org/packages/a1/88/7db0fe66d5aaf128443ee1623dec3db1576f3e4c17751ec0ef5866468590/lxml-6.1.0-cp312-cp312-manylinux_2_38_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:0f0f08beb0182e3e9a86fae124b3c47a7b41b7b69b225e1377db983802404e54", size = 5243901, upload-time = "2026-04-18T04:33:13.95Z" },
{ url = "https://files.pythonhosted.org/packages/00/a8/1346726af7d1f6fca1f11223ba34001462b0a3660416986d37641708d57c/lxml-6.1.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:73becf6d8c81d4c76b1014dbd3584cb26d904492dcf73ca85dc8bff08dcd6d2d", size = 5048054, upload-time = "2026-04-18T04:33:16.965Z" },
{ url = "https://files.pythonhosted.org/packages/2e/b7/85057012f035d1a0c87e02f8c723ca3c3e6e0728bcf4cb62080b21b1c1e3/lxml-6.1.0-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:1ae225f66e5938f4fa29d37e009a3bb3b13032ac57eb4eb42afa44f6e4054e69", size = 4777324, upload-time = "2026-04-18T04:33:19.832Z" },
{ url = "https://files.pythonhosted.org/packages/75/6c/ad2f94a91073ef570f33718040e8e160d5fb93331cf1ab3ca1323f939e2d/lxml-6.1.0-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:690022c7fae793b0489aa68a658822cea83e0d5933781811cabbf5ea3bcfe73d", size = 5645702, upload-time = "2026-04-18T04:33:22.436Z" },
{ url = "https://files.pythonhosted.org/packages/3b/89/0bb6c0bd549c19004c60eea9dc554dd78fd647b72314ef25d460e0d208c6/lxml-6.1.0-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:63aeafc26aac0be8aff14af7871249e87ea1319be92090bfd632ec68e03b16a5", size = 5232901, upload-time = "2026-04-18T04:33:26.21Z" },
{ url = "https://files.pythonhosted.org/packages/a1/d9/d609a11fb567da9399f525193e2b49847b5a409cdebe737f06a8b7126bdc/lxml-6.1.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:264c605ab9c0e4aa1a679636f4582c4d3313700009fac3ec9c3412ed0d8f3e1d", size = 5261333, upload-time = "2026-04-18T04:33:28.984Z" },
{ url = "https://files.pythonhosted.org/packages/a6/3a/ac3f99ec8ac93089e7dd556f279e0d14c24de0a74a507e143a2e4b496e7c/lxml-6.1.0-cp312-cp312-win32.whl", hash = "sha256:56971379bc5ee8037c5a0f09fa88f66cdb7d37c3e38af3e45cf539f41131ac1f", size = 3596289, upload-time = "2026-04-18T04:27:42.819Z" },
{ url = "https://files.pythonhosted.org/packages/f2/a7/0a915557538593cb1bbeedcd40e13c7a261822c26fecbbdb71dad0c2f540/lxml-6.1.0-cp312-cp312-win_amd64.whl", hash = "sha256:bba078de0031c219e5dd06cf3e6bf8fb8e6e64a77819b358f53bb132e3e03366", size = 3997059, upload-time = "2026-04-18T04:27:46.764Z" },
{ url = "https://files.pythonhosted.org/packages/92/96/a5dc078cf0126fbfbc35611d77ecd5da80054b5893e28fb213a5613b9e1d/lxml-6.1.0-cp312-cp312-win_arm64.whl", hash = "sha256:c3592631e652afa34999a088f98ba7dfc7d6aff0d535c410bea77a71743f3819", size = 3659552, upload-time = "2026-04-18T04:27:51.133Z" },
{ url = "https://files.pythonhosted.org/packages/08/03/69347590f1cf4a6d5a4944bb6099e6d37f334784f16062234e1f892fdb1d/lxml-6.1.0-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:a0092f2b107b69601adf562a57c956fbb596e05e3e6651cabd3054113b007e45", size = 8559689, upload-time = "2026-04-18T04:31:57.785Z" },
{ url = "https://files.pythonhosted.org/packages/3f/58/25e00bb40b185c974cfe156c110474d9a8a8390d5f7c92a4e328189bb60e/lxml-6.1.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:fc7140d7a7386e6b545d41b7358f4d02b656d4053f5fa6859f92f4b9c2572c4d", size = 4617892, upload-time = "2026-04-18T04:32:01.78Z" },
{ url = "https://files.pythonhosted.org/packages/f5/54/92ad98a94ac318dc4f97aaac22ff8d1b94212b2ae8af5b6e9b354bf825f7/lxml-6.1.0-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:419c58fc92cc3a2c3fa5f78c63dbf5da70c1fa9c1b25f25727ecee89a96c7de2", size = 4923489, upload-time = "2026-04-18T04:33:31.401Z" },
{ url = "https://files.pythonhosted.org/packages/15/3b/a20aecfab42bdf4f9b390590d345857ad3ffd7c51988d1c89c53a0c73faf/lxml-6.1.0-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:37fabd1452852636cf38ecdcc9dd5ca4bba7a35d6c53fa09725deeb894a87491", size = 5082162, upload-time = "2026-04-18T04:33:34.262Z" },
{ url = "https://files.pythonhosted.org/packages/45/26/2cdb3d281ac1bd175603e290cbe4bad6eff127c0f8de90bafd6f8548f0fd/lxml-6.1.0-cp313-cp313-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:a2853c8b2170cc6cd54a6b4d50d2c1a8a7aeca201f23804b4898525c7a152cfc", size = 4993247, upload-time = "2026-04-18T04:33:36.674Z" },
{ url = "https://files.pythonhosted.org/packages/f6/05/d735aef963740022a08185c84821f689fc903acb3d50326e6b1e9886cc22/lxml-6.1.0-cp313-cp313-manylinux_2_26_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:8e369cbd690e788c8d15e56222d91a09c6a417f49cbc543040cba0fe2e25a79e", size = 5613042, upload-time = "2026-04-18T04:33:39.205Z" },
{ url = "https://files.pythonhosted.org/packages/ee/b8/ead7c10efff731738c72e59ed6eb5791854879fbed7ae98781a12006263a/lxml-6.1.0-cp313-cp313-manylinux_2_26_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:e69aa6805905807186eb00e66c6d97a935c928275182eb02ee40ba00da9623b2", size = 5228304, upload-time = "2026-04-18T04:33:41.647Z" },
{ url = "https://files.pythonhosted.org/packages/6b/10/e9842d2ec322ea65f0a7270aa0315a53abed06058b88ef1b027f620e7a5f/lxml-6.1.0-cp313-cp313-manylinux_2_28_i686.whl", hash = "sha256:4bd1bdb8a9e0e2dd229de19b5f8aebac80e916921b4b2c6ef8a52bc131d0c1f9", size = 5341578, upload-time = "2026-04-18T04:33:44.596Z" },
{ url = "https://files.pythonhosted.org/packages/89/54/40d9403d7c2775fa7301d3ddd3464689bfe9ba71acc17dfff777071b4fdc/lxml-6.1.0-cp313-cp313-manylinux_2_31_armv7l.whl", hash = "sha256:cbd7b79cdcb4986ad78a2662625882747f09db5e4cd7b2ae178a88c9c51b3dfe", size = 4700209, upload-time = "2026-04-18T04:33:47.552Z" },
{ url = "https://files.pythonhosted.org/packages/85/b2/bbdcc2cf45dfc7dfffef4fd97e5c47b15919b6a365247d95d6f684ef5e82/lxml-6.1.0-cp313-cp313-manylinux_2_38_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:43e4d297f11080ec9d64a4b1ad7ac02b4484c9f0e2179d9c4ef78e886e747b88", size = 5232365, upload-time = "2026-04-18T04:33:50.249Z" },
{ url = "https://files.pythonhosted.org/packages/48/5a/b06875665e53aaba7127611a7bed3b7b9658e20b22bc2dd217a0b7ab0091/lxml-6.1.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:cc16682cc987a3da00aa56a3aa3075b08edb10d9b1e476938cfdbee8f3b67181", size = 5043654, upload-time = "2026-04-18T04:33:52.71Z" },
{ url = "https://files.pythonhosted.org/packages/e9/9c/e71a069d09641c1a7abeb30e693f828c7c90a41cbe3d650b2d734d876f85/lxml-6.1.0-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:d6d8efe71429635f0559579092bb5e60560d7b9115ee38c4adbea35632e7fa24", size = 4769326, upload-time = "2026-04-18T04:33:55.244Z" },
{ url = "https://files.pythonhosted.org/packages/cc/06/7a9cd84b3d4ed79adf35f874750abb697dec0b4a81a836037b36e47c091a/lxml-6.1.0-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:7e39ab3a28af7784e206d8606ec0e4bcad0190f63a492bca95e94e5a4aef7f6e", size = 5635879, upload-time = "2026-04-18T04:33:58.509Z" },
{ url = "https://files.pythonhosted.org/packages/cc/f0/9d57916befc1e54c451712c7ee48e9e74e80ae4d03bdce49914e0aee42cd/lxml-6.1.0-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:9eb667bf50856c4a58145f8ca2d5e5be160191e79eb9e30855a476191b3c3495", size = 5224048, upload-time = "2026-04-18T04:34:00.943Z" },
{ url = "https://files.pythonhosted.org/packages/99/75/90c4eefda0c08c92221fe0753db2d6699a4c628f76ff4465ec20dea84cc1/lxml-6.1.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:7f4a77d6f7edf9230cee3e1f7f6764722a41604ee5681844f18db9a81ea0ec33", size = 5250241, upload-time = "2026-04-18T04:34:03.365Z" },
{ url = "https://files.pythonhosted.org/packages/5e/73/16596f7e4e38fa33084b9ccbccc22a15f82a290a055126f2c1541236d2ff/lxml-6.1.0-cp313-cp313-win32.whl", hash = "sha256:28902146ffbe5222df411c5d19e5352490122e14447e98cd118907ee3fd6ee62", size = 3596938, upload-time = "2026-04-18T04:31:56.206Z" },
{ url = "https://files.pythonhosted.org/packages/8e/63/981401c5680c1eb30893f00a19641ac80db5d1e7086c62cb4b13ed813038/lxml-6.1.0-cp313-cp313-win_amd64.whl", hash = "sha256:4a1503c56e4e2b38dc76f2f2da7bae69670c0f1933e27cfa34b2fa5876410b16", size = 3995728, upload-time = "2026-04-18T04:31:58.763Z" },
{ url = "https://files.pythonhosted.org/packages/e7/e8/c358a38ac3e541d16a1b527e4e9cb78c0419b0506a070ace11777e5e8404/lxml-6.1.0-cp313-cp313-win_arm64.whl", hash = "sha256:e0af85773850417d994d019741239b901b22c6680206f46a34766926e466141d", size = 3658372, upload-time = "2026-04-18T04:32:03.629Z" },
{ url = "https://files.pythonhosted.org/packages/eb/45/cee4cf203ef0bab5c52afc118da61d6b460c928f2893d40023cfa27e0b80/lxml-6.1.0-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:ab863fd37458fed6456525f297d21239d987800c46e67da5ef04fc6b3dd93ac8", size = 8576713, upload-time = "2026-04-18T04:32:06.831Z" },
{ url = "https://files.pythonhosted.org/packages/8a/a7/eda05babeb7e046839204eaf254cd4d7c9130ce2bbf0d9e90ea41af5654d/lxml-6.1.0-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:6fd8b1df8254ff4fd93fd31da1fc15770bde23ac045be9bb1f87425702f61cc9", size = 4623874, upload-time = "2026-04-18T04:32:10.755Z" },
{ url = "https://files.pythonhosted.org/packages/e7/e9/db5846de9b436b91890a62f29d80cd849ea17948a49bf532d5278ee69a9e/lxml-6.1.0-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:47024feaae386a92a146af0d2aeed65229bf6fff738e6a11dda6b0015fb8fd03", size = 4949535, upload-time = "2026-04-18T04:34:06.657Z" },
{ url = "https://files.pythonhosted.org/packages/5a/ba/0d3593373dcae1d68f40dc3c41a5a92f2544e68115eb2f62319a4c2a6500/lxml-6.1.0-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:3f00972f84450204cd5d93a5395965e348956aaceaadec693a22ec743f8ae3eb", size = 5086881, upload-time = "2026-04-18T04:34:09.556Z" },
{ url = "https://files.pythonhosted.org/packages/43/76/759a7484539ad1af0d125a9afe9c3fb5f82a8779fd1f5f56319d9e4ea2fd/lxml-6.1.0-cp314-cp314-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:97faa0860e13b05b15a51fb4986421ef7a30f0b3334061c416e0981e9450ca4c", size = 5031305, upload-time = "2026-04-18T04:34:12.336Z" },
{ url = "https://files.pythonhosted.org/packages/dc/b9/c1f0daf981a11e47636126901fd4ab82429e18c57aeb0fc3ad2940b42d8b/lxml-6.1.0-cp314-cp314-manylinux_2_26_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:972a6451204798675407beaad97b868d0c733d9a74dafefc63120b81b8c2de28", size = 5647522, upload-time = "2026-04-18T04:34:14.89Z" },
{ url = "https://files.pythonhosted.org/packages/31/e6/1f533dcd205275363d9ba3511bcec52fa2df86abf8abe6a5f2c599f0dc31/lxml-6.1.0-cp314-cp314-manylinux_2_26_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:fe022f20bc4569ec66b63b3fb275a3d628d9d32da6326b2982584104db6d3086", size = 5239310, upload-time = "2026-04-18T04:34:17.652Z" },
{ url = "https://files.pythonhosted.org/packages/c3/8c/4175fb709c78a6e315ed814ed33be3defd8b8721067e70419a6cf6f971da/lxml-6.1.0-cp314-cp314-manylinux_2_28_i686.whl", hash = "sha256:75c4c7c619a744f972f4451bf5adf6d0fb00992a1ffc9fd78e13b0bc817cc99f", size = 5350799, upload-time = "2026-04-18T04:34:20.529Z" },
{ url = "https://files.pythonhosted.org/packages/fd/77/6ffdebc5994975f0dde4acb59761902bd9d9bb84422b9a0bd239a7da9ca8/lxml-6.1.0-cp314-cp314-manylinux_2_31_armv7l.whl", hash = "sha256:3648f20d25102a22b6061c688beb3a805099ea4beb0a01ce62975d926944d292", size = 4697693, upload-time = "2026-04-18T04:34:23.541Z" },
{ url = "https://files.pythonhosted.org/packages/f8/f1/565f36bd5c73294602d48e04d23f81ff4c8736be6ba5e1d1ec670ac9be80/lxml-6.1.0-cp314-cp314-manylinux_2_38_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:77b9f99b17cbf14026d1e618035077060fc7195dd940d025149f3e2e830fbfcb", size = 5250708, upload-time = "2026-04-18T04:34:26.001Z" },
{ url = "https://files.pythonhosted.org/packages/5a/11/a68ab9dd18c5c499404deb4005f4bc4e0e88e5b72cd755ad96efec81d18d/lxml-6.1.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:32662519149fd7a9db354175aa5e417d83485a8039b8aaa62f873ceee7ea4cad", size = 5084737, upload-time = "2026-04-18T04:34:28.32Z" },
{ url = "https://files.pythonhosted.org/packages/ab/78/e8f41e2c74f4af564e6a0348aea69fb6daaefa64bc071ef469823d22cc18/lxml-6.1.0-cp314-cp314-musllinux_1_2_armv7l.whl", hash = "sha256:73d658216fc173cf2c939e90e07b941c5e12736b0bf6a99e7af95459cfe8eabb", size = 4737817, upload-time = "2026-04-18T04:34:30.784Z" },
{ url = "https://files.pythonhosted.org/packages/06/2d/aa4e117aa2ce2f3b35d9ff246be74a2f8e853baba5d2a92c64744474603a/lxml-6.1.0-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:ac4db068889f8772a4a698c5980ec302771bb545e10c4b095d4c8be26749616f", size = 5670753, upload-time = "2026-04-18T04:34:33.675Z" },
{ url = "https://files.pythonhosted.org/packages/08/f5/dd745d50c0409031dbfcc4881740542a01e54d6f0110bd420fa7782110b8/lxml-6.1.0-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:45e9dfbd1b661eb64ba0d4dbe762bd210c42d86dd1e5bd2bdf89d634231beb43", size = 5238071, upload-time = "2026-04-18T04:34:36.12Z" },
{ url = "https://files.pythonhosted.org/packages/3e/74/ad424f36d0340a904665867dab310a3f1f4c96ff4039698de83b77f44c1f/lxml-6.1.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:89e8d73d09ac696a5ba42ec69787913d53284f12092f651506779314f10ba585", size = 5264319, upload-time = "2026-04-18T04:34:39.035Z" },
{ url = "https://files.pythonhosted.org/packages/53/36/a15d8b3514ec889bfd6aa3609107fcb6c9189f8dc347f1c0b81eded8d87c/lxml-6.1.0-cp314-cp314-win32.whl", hash = "sha256:ebe33f4ec1b2de38ceb225a1749a2965855bffeef435ba93cd2d5d540783bf2f", size = 3657139, upload-time = "2026-04-18T04:32:20.006Z" },
{ url = "https://files.pythonhosted.org/packages/1a/a4/263ebb0710851a3c6c937180a9a86df1206fdfe53cc43005aa2237fd7736/lxml-6.1.0-cp314-cp314-win_amd64.whl", hash = "sha256:398443df51c538bd578529aa7e5f7afc6c292644174b47961f3bf87fe5741120", size = 4064195, upload-time = "2026-04-18T04:32:23.876Z" },
{ url = "https://files.pythonhosted.org/packages/80/68/2000f29d323b6c286de077ad20b429fc52272e44eae6d295467043e56012/lxml-6.1.0-cp314-cp314-win_arm64.whl", hash = "sha256:8c8984e1d8c4b3949e419158fda14d921ff703a9ed8a47236c6eb7a2b6cb4946", size = 3741870, upload-time = "2026-04-18T04:32:27.922Z" },
{ url = "https://files.pythonhosted.org/packages/30/e9/21383c7c8d43799f0da90224c0d7c921870d476ec9b3e01e1b2c0b8237c5/lxml-6.1.0-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:1081dd10bc6fa437db2500e13993abf7cc30716d0a2f40e65abb935f02ec559c", size = 8827548, upload-time = "2026-04-18T04:32:15.094Z" },
{ url = "https://files.pythonhosted.org/packages/a5/01/c6bc11cd587030dd4f719f65c5657960649fe3e19196c844c75bf32cd0d6/lxml-6.1.0-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:dabecc48db5f42ba348d1f5d5afdc54c6c4cc758e676926c7cd327045749517d", size = 4735866, upload-time = "2026-04-18T04:32:18.924Z" },
{ url = "https://files.pythonhosted.org/packages/f3/01/757132fff5f4acf25463b5298f1a46099f3a94480b806547b29ce5e385de/lxml-6.1.0-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:e3dd5fe19c9e0ac818a9c7f132a5e43c1339ec1cbbfecb1a938bd3a47875b7c9", size = 4969476, upload-time = "2026-04-18T04:34:41.889Z" },
{ url = "https://files.pythonhosted.org/packages/fd/fb/1bc8b9d27ed64be7c8903db6c89e74dc8c2cd9ec630a7462e4654316dc5b/lxml-6.1.0-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:9e7b0a4ca6dcc007a4cef00a761bba2dea959de4bd2df98f926b33c92ca5dfb9", size = 5103719, upload-time = "2026-04-18T04:34:44.797Z" },
{ url = "https://files.pythonhosted.org/packages/d5/e7/5bf82fa28133536a54601aae633b14988e89ed61d4c1eb6b899b023233aa/lxml-6.1.0-cp314-cp314t-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5d27bbe326c6b539c64b42638b18bc6003a8d88f76213a97ac9ed4f885efeab7", size = 5027890, upload-time = "2026-04-18T04:34:47.634Z" },
{ url = "https://files.pythonhosted.org/packages/2d/20/e048db5d4b4ea0366648aa595f26bb764b2670903fc585b87436d0a5032c/lxml-6.1.0-cp314-cp314t-manylinux_2_26_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:c4e425db0c5445ef0ad56b0eec54f89b88b2d884656e536a90b2f52aecb4ca86", size = 5596008, upload-time = "2026-04-18T04:34:51.503Z" },
{ url = "https://files.pythonhosted.org/packages/9a/c2/d10807bc8da4824b39e5bd01b5d05c077b6fd01bd91584167edf6b269d22/lxml-6.1.0-cp314-cp314t-manylinux_2_26_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:4b89b098105b8599dc57adac95d1813409ac476d3c948a498775d3d0c6124bfb", size = 5224451, upload-time = "2026-04-18T04:34:54.263Z" },
{ url = "https://files.pythonhosted.org/packages/3c/15/2ebea45bea427e7f0057e9ce7b2d62c5aba20c6b001cca89ed0aadb3ad41/lxml-6.1.0-cp314-cp314t-manylinux_2_28_i686.whl", hash = "sha256:c4a699432846df86cc3de502ee85f445ebad748a1c6021d445f3e514d2cd4b1c", size = 5312135, upload-time = "2026-04-18T04:34:56.818Z" },
{ url = "https://files.pythonhosted.org/packages/31/e2/87eeae151b0be2a308d49a7ec444ff3eb192b14251e62addb29d0bf3778f/lxml-6.1.0-cp314-cp314t-manylinux_2_31_armv7l.whl", hash = "sha256:30e7b2ed63b6c8e97cca8af048589a788ab5c9c905f36d9cf1c2bb549f450d2f", size = 4639126, upload-time = "2026-04-18T04:34:59.704Z" },
{ url = "https://files.pythonhosted.org/packages/a3/51/8a3f6a20902ad604dd746ec7b4000311b240d389dac5e9d95adefd349e0c/lxml-6.1.0-cp314-cp314t-manylinux_2_38_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:022981127642fe19866d2907d76241bb07ed21749601f727d5d5dd1ce5d1b773", size = 5232579, upload-time = "2026-04-18T04:35:02.658Z" },
{ url = "https://files.pythonhosted.org/packages/6d/d2/650d619bdbe048d2c3f2c31edb00e35670a5e2d65b4fe3b61bce37b19121/lxml-6.1.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:23cad0cc86046d4222f7f418910e46b89971c5a45d3c8abfad0f64b7b05e4a9b", size = 5084206, upload-time = "2026-04-18T04:35:05.175Z" },
{ url = "https://files.pythonhosted.org/packages/dd/8a/672ca1a3cbeabd1f511ca275a916c0514b747f4b85bdaae103b8fa92f307/lxml-6.1.0-cp314-cp314t-musllinux_1_2_armv7l.whl", hash = "sha256:21c3302068f50d1e8728c67c87ba92aa87043abee517aa2576cca1855326b405", size = 4758906, upload-time = "2026-04-18T04:35:08.098Z" },
{ url = "https://files.pythonhosted.org/packages/be/f1/ef4b691da85c916cb2feb1eec7414f678162798ac85e042fa164419ac05c/lxml-6.1.0-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:be10838781cb3be19251e276910cd508fe127e27c3242e50521521a0f3781690", size = 5620553, upload-time = "2026-04-18T04:35:11.23Z" },
{ url = "https://files.pythonhosted.org/packages/59/17/94e81def74107809755ac2782fdad4404420f1c92ca83433d117a6d5acf0/lxml-6.1.0-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:2173a7bffe97667bbf0767f8a99e587740a8c56fdf3befac4b09cb29a80276fd", size = 5229458, upload-time = "2026-04-18T04:35:14.254Z" },
{ url = "https://files.pythonhosted.org/packages/21/55/c4be91b0f830a871fc1b0d730943d56013b683d4671d5198260e2eae722b/lxml-6.1.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:c6854e9cf99c84beb004eecd7d3a3868ef1109bf2b1df92d7bc11e96a36c2180", size = 5247861, upload-time = "2026-04-18T04:35:17.006Z" },
{ url = "https://files.pythonhosted.org/packages/c2/ca/77123e4d77df3cb1e968ade7b1f808f5d3a5c1c96b18a33895397de292c1/lxml-6.1.0-cp314-cp314t-win32.whl", hash = "sha256:00750d63ef0031a05331b9223463b1c7c02b9004cef2346a5b2877f0f9494dd2", size = 3897377, upload-time = "2026-04-18T04:32:07.656Z" },
{ url = "https://files.pythonhosted.org/packages/64/ce/3554833989d074267c063209bae8b09815e5656456a2d332b947806b05ff/lxml-6.1.0-cp314-cp314t-win_amd64.whl", hash = "sha256:80410c3a7e3c617af04de17caa9f9f20adaa817093293d69eae7d7d0522836f5", size = 4392701, upload-time = "2026-04-18T04:32:12.113Z" },
{ url = "https://files.pythonhosted.org/packages/2b/a0/9b916c68c0e57752c07f8f64b30138d9d4059dbeb27b90274dedbea128ff/lxml-6.1.0-cp314-cp314t-win_arm64.whl", hash = "sha256:26dd9f57ee3bd41e7d35b4c98a2ffd89ed11591649f421f0ec19f67d50ec67ac", size = 3817120, upload-time = "2026-04-18T04:32:15.803Z" },
]
[[package]]
name = "marimo"
version = "0.20.4"
@@ -2842,6 +2931,22 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/6f/2c/5b079febdc65e1c3fb2729bf958d18b45be7113828528e8a0b5850dd819a/pymdown_extensions-10.21-py3-none-any.whl", hash = "sha256:91b879f9f864d49794c2d9534372b10150e6141096c3908a455e45ca72ad9d3f", size = 268877, upload-time = "2026-02-15T20:44:05.464Z" },
]
[[package]]
name = "pymupdf"
version = "1.27.2.2"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/f1/32/f6b645c51d79a188a4844140c5dabca7b487ad56c4be69c4bc782d0d11a9/pymupdf-1.27.2.2.tar.gz", hash = "sha256:ea8fdc3ab6671ca98f629d5ec3032d662c8cf1796b146996b7ad306ac7ed3335", size = 85354380, upload-time = "2026-03-20T09:47:58.386Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/90/88/d01992a50165e22dec057a1129826846c547feb4ba07f42720ac030ce438/pymupdf-1.27.2.2-cp310-abi3-macosx_10_9_x86_64.whl", hash = "sha256:800f43e60a6f01f644343c2213b8613db02eaf4f4ba235b417b3351fa99e01c0", size = 23987563, upload-time = "2026-03-19T12:35:42.989Z" },
{ url = "https://files.pythonhosted.org/packages/6d/0e/9f526bc1d49d8082eff0d1547a69d541a0c5a052e71da625559efaba46a6/pymupdf-1.27.2.2-cp310-abi3-macosx_11_0_arm64.whl", hash = "sha256:8e2e4299ef1ac0c9dff9be096cbd22783699673abecfa7c3f73173ae06421d73", size = 23263089, upload-time = "2026-03-20T09:44:16.982Z" },
{ url = "https://files.pythonhosted.org/packages/42/be/984f0d6343935b5dd30afaed6be04fc753146bf55709e63ef28bf9ef7497/pymupdf-1.27.2.2-cp310-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:c5e3d54922db1c7da844f1208ac1db05704770988752311f81dd36694ae0a07b", size = 24318817, upload-time = "2026-03-20T09:44:33.209Z" },
{ url = "https://files.pythonhosted.org/packages/22/8e/85e9d9f11dbf34036eb1df283805ef6b885f2005a56d6533bb58ab0b8a11/pymupdf-1.27.2.2-cp310-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:892698c9768457eb0991c102c96a856c0a7062539371df5e6bee0816f3ef498e", size = 24948135, upload-time = "2026-03-20T09:44:51.012Z" },
{ url = "https://files.pythonhosted.org/packages/db/e6/386edb017e5b93f1ab0bf6653ae32f3dd8dfc834ed770212e10ca62f4af9/pymupdf-1.27.2.2-cp310-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:8b4bbfa6ef347fade678771a93f6364971c51a2cdc44cd2400dc4eeed1ddb4e6", size = 25169585, upload-time = "2026-03-20T09:45:05.393Z" },
{ url = "https://files.pythonhosted.org/packages/ba/fd/f1ebe24fcd31aaea8b85b3a7ac4c3fc96e20388be5466ace27c9a3c546d9/pymupdf-1.27.2.2-cp310-abi3-win32.whl", hash = "sha256:0b8e924433b7e0bd46be820899300259235997d5a747638471fb2762baa8ee30", size = 18008861, upload-time = "2026-03-20T09:45:21.353Z" },
{ url = "https://files.pythonhosted.org/packages/a8/b6/2a9a8556000199bbf80a5915dcd15d550d1e5288894316445c54726aaf53/pymupdf-1.27.2.2-cp310-abi3-win_amd64.whl", hash = "sha256:09bb53f9486ccb5297030cbc2dbdae845ba1c3c5126e96eb2d16c4f118de0b5b", size = 19238032, upload-time = "2026-03-20T09:45:37.941Z" },
{ url = "https://files.pythonhosted.org/packages/c2/c6/e3e11c42f09b9c34ec332c0f37b817671b59ef4001895b854f0494092105/pymupdf-1.27.2.2-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:6cebfbbdfd219ebdebf4d8e3914624b2e3d3a844c43f4f76935822dd9b13cc12", size = 24985299, upload-time = "2026-03-20T09:45:53.26Z" },
]
[[package]]
name = "pypdfium2"
version = "5.5.0"
@@ -2901,6 +3006,19 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/ee/49/1377b49de7d0c1ce41292161ea0f721913fa8722c19fb9c1e3aa0367eecb/pytest_cov-7.0.0-py3-none-any.whl", hash = "sha256:3b8e9558b16cc1479da72058bdecf8073661c7f57f7d3c5f22a1c23507f2d861", size = 22424, upload-time = "2025-09-09T10:57:00.695Z" },
]
[[package]]
name = "pytest-xdist"
version = "3.8.0"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "execnet" },
{ name = "pytest" },
]
sdist = { url = "https://files.pythonhosted.org/packages/78/b4/439b179d1ff526791eb921115fca8e44e596a13efeda518b9d845a619450/pytest_xdist-3.8.0.tar.gz", hash = "sha256:7e578125ec9bc6050861aa93f2d59f1d8d085595d6551c2c90b6f4fad8d3a9f1", size = 88069, upload-time = "2025-07-01T13:30:59.346Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/ca/31/d4e37e9e550c2b92a9cbc2e4d0b7420a27224968580b5a447f420847c975/pytest_xdist-3.8.0-py3-none-any.whl", hash = "sha256:202ca578cfeb7370784a8c33d6d05bc6e13b4f25b5053c30a152269fd10f0b88", size = 46396, upload-time = "2025-07-01T13:30:56.632Z" },
]
[[package]]
name = "python-dateutil"
version = "2.9.0.post0"
@@ -2913,6 +3031,19 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/ec/57/56b9bcc3c9c6a792fcbaf139543cee77261f3651ca9da0c93f5c1221264b/python_dateutil-2.9.0.post0-py2.py3-none-any.whl", hash = "sha256:a8b2bc7bffae282281c8140a97d3aa9c14da0b136dfe83f850eea9a5f7470427", size = 229892, upload-time = "2024-03-01T18:36:18.57Z" },
]
[[package]]
name = "python-docx"
version = "1.2.0"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "lxml" },
{ name = "typing-extensions" },
]
sdist = { url = "https://files.pythonhosted.org/packages/a9/f7/eddfe33871520adab45aaa1a71f0402a2252050c14c7e3009446c8f4701c/python_docx-1.2.0.tar.gz", hash = "sha256:7bc9d7b7d8a69c9c02ca09216118c86552704edc23bac179283f2e38f86220ce", size = 5723256, upload-time = "2025-06-16T20:46:27.921Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/d0/00/1e03a4989fa5795da308cd774f05b704ace555a70f9bf9d3be057b680bcf/python_docx-1.2.0-py3-none-any.whl", hash = "sha256:3fd478f3250fbbbfd3b94fe1e985955737c145627498896a8a6bf81f4baf66c7", size = 252987, upload-time = "2025-06-16T20:46:22.506Z" },
]
[[package]]
name = "python-slugify"
version = "8.0.4"
@@ -3274,6 +3405,8 @@ version = "0.1.0"
source = { editable = "." }
dependencies = [
{ name = "pydantic" },
{ name = "pymupdf" },
{ name = "python-docx" },
{ name = "xlrd" },
]
@@ -3462,6 +3595,7 @@ dev = [
{ name = "polars" },
{ name = "pytest" },
{ name = "pytest-cov" },
{ name = "pytest-xdist" },
{ name = "ruff" },
{ name = "s3fs" },
{ name = "stack", extra = ["all"] },
@@ -3518,6 +3652,8 @@ requires-dist = [
{ name = "pydo", marker = "extra == 'mail'", specifier = ">=0.29.0" },
{ name = "pydo", marker = "extra == 'prisma'", specifier = ">=0.29.0" },
{ name = "pyjwt", marker = "extra == 'api'", specifier = ">=2.12.0" },
{ name = "pymupdf", specifier = ">=1.24" },
{ name = "python-docx", specifier = ">=1.1" },
{ name = "pyyaml", marker = "extra == 'prisma'", specifier = ">=6.0.0" },
{ name = "resend", marker = "extra == 'mail'", specifier = ">=2.0.0" },
{ name = "resend", marker = "extra == 'prisma'", specifier = ">=2.0.0" },
@@ -3579,6 +3715,7 @@ dev = [
{ name = "polars", specifier = ">=1.38.1" },
{ name = "pytest", specifier = ">=9.0.2" },
{ name = "pytest-cov", specifier = ">=7.0.0" },
{ name = "pytest-xdist", specifier = ">=3.5.0" },
{ name = "ruff", specifier = ">=0.11.0" },
{ name = "s3fs", specifier = ">=2026.2.0" },
{ name = "stack", extras = ["all"] },