Update artifact actions

.github/workflows/build.yml

@@ -225,8 +225,9 @@ jobs:
           python -m pip install --upgrade pip wheel build
           python -m build --sdist --wheel
 
-      - uses: actions/upload-artifact@v3
+      - uses: actions/upload-artifact@v4
         with:
+          name: artifact
           path: |
             ./dist/*.whl
             ./dist/*.tar.gz
@@ -240,9 +241,8 @@ jobs:
       id-token: write  # mandatory for PyPI publishing
     if: github.event_name == 'push' && startsWith(github.event.ref, 'refs/tags/v')
     steps:
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4
         with:
-          name: artifact
           path: dist
 
       - name: Publish to PyPI
@@ -257,9 +257,8 @@ jobs:
       # Required to create a release
       contents: write
     steps:
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4
         with:
-          name: artifact
           path: dist
 
       - name: Create Release

docs/release_notes.rst

@@ -30,8 +30,15 @@ OCRmyPDF typically supports the three most recent Python versions.
 
 .. |OCRmyPDF PyPI| image:: https://img.shields.io/pypi/v/ocrmypdf.svg
 
-v16.0.0rc1
+v16.0.1
-==========
+=======
+
+-  Fixed text rendering issue with new hOCR text renderer - extraneous byte order
+   marks.
+-  Tightened dependencies.
+
+v16.0.0
+=======
 
 -  Added OCR text renderer, combined the best ideas of Tesseract's PDF
    generator and the older hOCR transformer renderer. The result is a hopefully

pyproject.toml

@@ -14,11 +14,11 @@ requires-python = ">=3.10"
 dependencies = [
   "Pillow>=10.0.1",
   "deprecation>=2.1.0",
-  "img2pdf>=0.4.4",
+  "img2pdf>=0.5",
   "packaging>=20",
   "pdfminer.six>=20220319",
-  "pikepdf>=8.8.0",
+  "pikepdf>=8.10.1",
-  "pluggy>=0.13.0",
+  "pluggy>=1",
   "rich>=13",
 ]
 authors = [{ name = "James R. Barlow", email = "james@purplerock.ca" }]

src/ocrmypdf/hocrtransform/_hocr.py

@@ -106,10 +106,10 @@ class HocrTransform:
         self.render_options = DebugRenderOptions(
             render_baseline=debug,
             render_triangle=debug,
-            render_line_bbox=debug,
+            render_line_bbox=False,
             render_word_bbox=debug,
-            render_paragraph_bbox=debug,
+            render_paragraph_bbox=False,
-            render_space_bbox=debug,
+            render_space_bbox=False,
         )
 
     def _get_element_text(self, element: Element):
@@ -365,7 +365,7 @@ class HocrTransform:
         if font_width > 0:
             text.text_transform(Matrix(1, 0, 0, 1, box.llx, 0))
             text.horiz_scale(100 * box.width / font_width)
-            text.show(elemtxt)
+            text.show(elemtxt.encode('utf-16be'))
 
         # Get coordinates of the next word (if there is one)
         hocr_next_box = (
@@ -389,7 +389,7 @@ class HocrTransform:
         space_width = self._font.text_width(' ', fontsize)
         if space_width > 0:
             text.horiz_scale(100 * space_box.width / space_width)
-            text.show(' ')
+            text.show(' '.encode('utf-16be'))
 
     def _debug_draw_paragraph_boxes(self, canvas: Canvas, color=CYAN):
         """Draw boxes around paragraphs in the document."""