Refactor: move ocr_element to a better location

src/ocrmypdf/__init__.py

@@ -35,7 +35,7 @@ from ocrmypdf.exceptions import (
     TesseractConfigError,
     UnsupportedImageFormatError,
 )
-from ocrmypdf.hocrtransform import (
+from ocrmypdf.models.ocr_element import (
     Baseline,
     BoundingBox,
     FontInfo,

src/ocrmypdf/fpdf_renderer/renderer.py

@@ -20,7 +20,7 @@ from fpdf.enums import TextMode
 from pikepdf import Matrix, Rectangle
 
 from ocrmypdf.font import FontManager, MultiFontManager
-from ocrmypdf.hocrtransform.ocr_element import OcrClass, OcrElement
+from ocrmypdf.models.ocr_element import OcrClass, OcrElement
 
 log = logging.getLogger(__name__)
 

src/ocrmypdf/hocrtransform/__init__.py

@@ -27,7 +27,7 @@ from ocrmypdf.hocrtransform.hocr_parser import (
     HocrParseError,
     HocrParser,
 )
-from ocrmypdf.hocrtransform.ocr_element import (
+from ocrmypdf.models.ocr_element import (
     Baseline,
     BoundingBox,
     FontInfo,

src/ocrmypdf/hocrtransform/hocr_parser.py

@@ -20,9 +20,9 @@ import re
 import unicodedata
 from pathlib import Path
 from typing import Literal, cast
-from xml.etree import ElementTree
+from xml.etree import ElementTree as ET
 
-from ocrmypdf.hocrtransform.ocr_element import (
+from ocrmypdf.models.ocr_element import (
     Baseline,
     BoundingBox,
     FontInfo,
@@ -34,7 +34,7 @@ TextDirection = Literal["ltr", "rtl"]
 
 log = logging.getLogger(__name__)
 
-Element = ElementTree.Element
+Element = ET.Element
 
 
 class HocrParseError(Exception):
@@ -132,8 +132,8 @@ class HocrParser:
         """
         self._hocr_path = Path(hocr_file)
         try:
-            self._tree = ElementTree.parse(os.fspath(hocr_file))
-        except ElementTree.ParseError as e:
+            self._tree = ET.parse(os.fspath(hocr_file))
+        except ET.ParseError as e:
             raise HocrParseError(f"Failed to parse hOCR file: {e}") from e
 
         # Detect XML namespace

src/ocrmypdf/models/__init__.py

@@ -0,0 +1,6 @@
+# SPDX-FileCopyrightText: 2025 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+"""OCRmyPDF models for plugin options and cross-cutting concerns."""
+
+from __future__ import annotations

tests/test_fpdf_renderer.py

@@ -16,7 +16,7 @@ from ocrmypdf.fpdf_renderer import (
     Fpdf2PdfRenderer,
 )
 from ocrmypdf.hocrtransform.hocr_parser import HocrParser
-from ocrmypdf.hocrtransform.ocr_element import OcrClass
+from ocrmypdf.models.ocr_element import OcrClass
 
 
 @pytest.fixture
@@ -80,7 +80,7 @@ class TestFpdf2PdfRenderer:
 
     def test_requires_page_element(self, multi_font_manager):
         """Test that renderer requires ocr_page element."""
-        from ocrmypdf.hocrtransform.ocr_element import BoundingBox, OcrElement
+        from ocrmypdf.models.ocr_element import BoundingBox, OcrElement
 
         # Create a non-page element
         word = OcrElement(
@@ -98,7 +98,7 @@ class TestFpdf2PdfRenderer:
 
     def test_requires_bbox(self, multi_font_manager):
         """Test that renderer requires page with bounding box."""
-        from ocrmypdf.hocrtransform.ocr_element import OcrElement
+        from ocrmypdf.models.ocr_element import OcrElement
 
         page = OcrElement(ocr_class=OcrClass.PAGE)
 
@@ -111,7 +111,7 @@ class TestFpdf2PdfRenderer:
 
     def test_render_simple_page(self, multi_font_manager, tmp_path):
         """Test rendering a simple page with one word."""
-        from ocrmypdf.hocrtransform.ocr_element import BoundingBox, OcrElement
+        from ocrmypdf.models.ocr_element import BoundingBox, OcrElement
 
         # Create a simple page with one word
         word = OcrElement(
@@ -145,7 +145,7 @@ class TestFpdf2PdfRenderer:
 
     def test_render_invisible_text(self, multi_font_manager, tmp_path):
         """Test rendering invisible text (OCR layer)."""
-        from ocrmypdf.hocrtransform.ocr_element import BoundingBox, OcrElement
+        from ocrmypdf.models.ocr_element import BoundingBox, OcrElement
 
         word = OcrElement(
             ocr_class=OcrClass.WORD,
@@ -191,7 +191,7 @@ class TestFpdf2MultiPageRenderer:
 
     def test_render_multiple_pages(self, multi_font_manager, tmp_path):
         """Test rendering multiple pages."""
-        from ocrmypdf.hocrtransform.ocr_element import BoundingBox, OcrElement
+        from ocrmypdf.models.ocr_element import BoundingBox, OcrElement
 
         pages_data = []
         for i in range(3):
@@ -385,7 +385,7 @@ class TestWordSegmentation:
         """
         from pdfminer.high_level import extract_text
 
-        from ocrmypdf.hocrtransform.ocr_element import BoundingBox, OcrElement
+        from ocrmypdf.models.ocr_element import BoundingBox, OcrElement
 
         # Create a page with multiple words on one line
         word1 = OcrElement(
@@ -451,7 +451,7 @@ class TestWordSegmentation:
         """
         from pdfminer.high_level import extract_text
 
-        from ocrmypdf.hocrtransform.ocr_element import BoundingBox, OcrElement
+        from ocrmypdf.models.ocr_element import BoundingBox, OcrElement
 
         # Create a page with CJK words (Chinese characters)
         # 你好 = "Hello" in Chinese