Tighten ruff rules and modernize style

src/ocrmypdf/_defaults.py

@@ -2,6 +2,8 @@
 # SPDX-License-Identifier: MPL-2.0
 
 # Enforce English hegemony
+from __future__ import annotations
+
 DEFAULT_LANGUAGE = 'eng'
 
 # Default rotation threshold

src/ocrmypdf/_exec/ghostscript.py

@@ -111,6 +111,15 @@ def rasterize_pdf(
     """Rasterize one page of a PDF at resolution raster_dpi in canvas units.
 
     Args:
+        input_file: The PDF file to rasterize.
+        output_file: The file to write the rasterized PDF to.
+        raster_device: The Ghostscript raster device to use to rasterize the PDF.
+        raster_dpi: Resolution in dots per inch at which to rasterize page.
+        pageno: Page number to rasterize (beginning at page 1).
+        page_dpi: Resolution, overriding output image DPI.
+        rotation: Cardinal angle, clockwise, to rotate page.
+        filter_vector: If True, remove vector graphics objects.
+        stop_on_error: If True, stop rasterizing on the first error.
         use_cropbox: If True, rasterize the CropBox instead of MediaBox.
             Default is False (use MediaBox).
     """

src/ocrmypdf/_metadata.py

@@ -5,9 +5,9 @@
 
 from __future__ import annotations
 
+import datetime as dt
 import logging
 import os
-from datetime import datetime, timezone
 from pathlib import Path
 from typing import Any
 
@@ -53,7 +53,7 @@ def get_docinfo(base_pdf: Pdf, context: PdfContext) -> dict[str, str]:
 
     pdfmark['/Creator'] = f'{PROGRAM_NAME} {OCRMYPF_VERSION} / {creator_tag}'
     pdfmark['/Producer'] = f'pikepdf {PIKEPDF_VERSION}'
-    pdfmark['/ModDate'] = encode_pdf_date(datetime.now(timezone.utc))
+    pdfmark['/ModDate'] = encode_pdf_date(dt.datetime.now(dt.UTC))
     return pdfmark
 
 

src/ocrmypdf/_pipelines/ocr.py

@@ -50,7 +50,7 @@ from ocrmypdf._validation import (
 )
 from ocrmypdf.exceptions import ExitCode
 from ocrmypdf.helpers import available_cpu_count
-from ocrmypdf.hocrtransform.ocr_element import OcrElement
+from ocrmypdf.models.ocr_element import OcrElement
 
 log = logging.getLogger(__name__)
 

src/ocrmypdf/font/__init__.py

@@ -10,6 +10,7 @@ This module provides font infrastructure for the fpdf2 PDF renderer. It includes
 - MultiFontManager: Automatic font selection for multilingual documents
 - SystemFontProvider: System font discovery
 """
+from __future__ import annotations
 
 from ocrmypdf.font.font_manager import FontManager
 from ocrmypdf.font.font_provider import (

src/ocrmypdf/fpdf_renderer/__init__.py

@@ -6,6 +6,7 @@
 This module provides the PDF renderer using fpdf2 for creating
 searchable OCR text layers.
 """
+from __future__ import annotations
 
 from ocrmypdf.fpdf_renderer.renderer import (
     DebugRenderOptions,

src/ocrmypdf/helpers.py

@@ -25,7 +25,6 @@ from typing import (
 
 import img2pdf
 import pikepdf
-from deprecation import deprecated
 
 log = logging.getLogger(__name__)
 

src/ocrmypdf/hocrtransform/__main__.py

@@ -2,6 +2,7 @@
 # SPDX-License-Identifier: MIT
 
 """Simple CLI for testing HOCR to PDF conversion using fpdf2 renderer."""
+from __future__ import annotations
 
 import argparse
 from pathlib import Path

src/ocrmypdf/languages.py

@@ -6,6 +6,7 @@
 Derived from
 https://www.loc.gov/standards/iso639-2/ascii_8bits.html
 """
+from __future__ import annotations
 
 from typing import NamedTuple