standardize packaging, tooling, docs, CI, and licensing

tests/conftest.py

@@ -1,22 +1,20 @@
 import json
-import pytest
-import httpx
 from pathlib import Path
-from jinja2 import Environment, BaseLoader
+
+import httpx
+import pytest
+from jinja2 import BaseLoader, Environment
 
 from omniread import (
     # core
     ContentType,
-
-    # html
-    HTMLScraper,
-
     # pdf
     FileSystemPDFClient,
+    # html
+    HTMLScraper,
     PDFScraper,
 )
 
-
 MOCK_HTML_DIR = Path(__file__).parent / "mocks" / "html"
 MOCK_PDF_DIR = Path(__file__).parent / "mocks" / "pdf"
 
@@ -40,7 +38,7 @@ def mock_transport(request: httpx.Request) -> httpx.Response:
     httpx MockTransport handler.
     """
     path = request.url.path
-    if path not in ['/simple', '/table']:
+    if path not in ["/simple", "/table"]:
         return httpx.Response(
             status_code=404,
             content=b"Not Found",

tests/test_html_simple.py

@@ -1,22 +1,19 @@
-from typing import Optional
-
-from pydantic import BaseModel
 from bs4 import Tag
+from pydantic import BaseModel
 
 from omniread import (
     # core
     Content,
-
     # html
     HTMLParser,
 )
 
 
 class ParsedSimpleHTML(BaseModel):
-    title: Optional[str]
-    description: Optional[str]
-    content: Optional[str]
-    link: Optional[str]
+    title: str | None
+    description: str | None
+    content: str | None
+    link: str | None
 
 
 class SimpleHTMLParser(HTMLParser[ParsedSimpleHTML]):

tests/test_html_table.py

@@ -1,18 +1,15 @@
-from typing import Optional
-
 from pydantic import BaseModel
 
 from omniread import (
     # core
     Content,
-
     # html
     HTMLParser,
 )
 
 
 class ParsedTableHTML(BaseModel):
-    title: Optional[str]
+    title: str | None
     table: list[list[str]]
 
 

tests/test_pdf_simple.py

@@ -1,14 +1,15 @@
 from typing import Literal
+
 from pydantic import BaseModel
 
 from omniread import (
     # core
     Content,
-
     # pdf
     PDFParser,
 )
 
+
 class ParsedPDF(BaseModel):
     size_bytes: int
     magic: Literal[b"%PDF"]

tests/test_xlsx_simple.py

@@ -8,7 +8,6 @@ from omniread import (
     # core
     Content,
     ContentType,
-
     # xlsx
     FileSystemXlsxClient,
     XlsxParser,
@@ -22,8 +21,28 @@ def _fixture_xlsx_bytes() -> bytes:
     ws.title = "Statement"
     ws.append(["DETAILED STATEMENT", None, None, ""])
     ws.append([])
-    ws.append(["S No", "Value Date", "Txn Date", "Remarks", "Withdrawal", "Deposit", "Balance"])
-    ws.append([1, "01/06/2026", "01/06/2026", "UPI/NPCI BHIM/bhimcashback@h/B", 0.0, 10.0, 250285.24])
+    ws.append(
+        [
+            "S No",
+            "Value Date",
+            "Txn Date",
+            "Remarks",
+            "Withdrawal",
+            "Deposit",
+            "Balance",
+        ]
+    )
+    ws.append(
+        [
+            1,
+            "01/06/2026",
+            "01/06/2026",
+            "UPI/NPCI BHIM/bhimcashback@h/B",
+            0.0,
+            10.0,
+            250285.24,
+        ]
+    )
     row = 4
     ws.cell(row=row, column=5).value = 100.0  # ensure float rendering path
     buf = BytesIO()
@@ -68,7 +87,9 @@ def test_client_directory_raises(tmp_path):
 
 
 def test_parser_rows_skip_empty_and_trim(xlsx_bytes):
-    parser = XlsxParser(Content(raw=xlsx_bytes, source="mem", content_type=ContentType.XLSX))
+    parser = XlsxParser(
+        Content(raw=xlsx_bytes, source="mem", content_type=ContentType.XLSX)
+    )
 
     rows = parser.rows()
 
@@ -76,14 +97,24 @@ def test_parser_rows_skip_empty_and_trim(xlsx_bytes):
     assert len(rows) == 3
     assert rows[0] == ["DETAILED STATEMENT"]
     header = rows[1]
-    assert header[:7] == ["S No", "Value Date", "Txn Date", "Remarks", "Withdrawal", "Deposit", "Balance"]
+    assert header[:7] == [
+        "S No",
+        "Value Date",
+        "Txn Date",
+        "Remarks",
+        "Withdrawal",
+        "Deposit",
+        "Balance",
+    ]
     data = rows[2]
     assert data[3] == "UPI/NPCI BHIM/bhimcashback@h/B"
     assert data[6] == "250285.24"
 
 
 def test_parser_keep_empty_rows(xlsx_bytes):
-    parser = XlsxParser(Content(raw=xlsx_bytes, source="mem", content_type=ContentType.XLSX))
+    parser = XlsxParser(
+        Content(raw=xlsx_bytes, source="mem", content_type=ContentType.XLSX)
+    )
 
     rows = parser.rows(skip_empty=False)
 
@@ -91,7 +122,9 @@ def test_parser_keep_empty_rows(xlsx_bytes):
 
 
 def test_parser_sheet_selection_and_names(xlsx_bytes):
-    parser = XlsxParser(Content(raw=xlsx_bytes, source="mem", content_type=ContentType.XLSX))
+    parser = XlsxParser(
+        Content(raw=xlsx_bytes, source="mem", content_type=ContentType.XLSX)
+    )
 
     assert parser.sheet_names == ["Statement"]
     assert parser.rows(sheet="Statement") == parser.rows(sheet=0)
@@ -108,11 +141,15 @@ def test_parser_date_cell_isoformat():
     buf = BytesIO()
     wb.save(buf)
 
-    parser = XlsxParser(Content(raw=buf.getvalue(), source="mem", content_type=ContentType.XLSX))
+    parser = XlsxParser(
+        Content(raw=buf.getvalue(), source="mem", content_type=ContentType.XLSX)
+    )
     # openpyxl surfaces date cells as datetime; ISO rendering keeps determinism
     assert parser.parse()[0][0] == "2026-06-01T00:00:00"
 
 
 def test_parser_rejects_non_xlsx_content():
     with pytest.raises(ValueError, match="does not support"):
-        XlsxParser(Content(raw=b"<html></html>", source="mem", content_type=ContentType.HTML))
+        XlsxParser(
+            Content(raw=b"<html></html>", source="mem", content_type=ContentType.HTML)
+        )