Update issue template

.github/ISSUE_TEMPLATE/1-bug-report-general.yml

@@ -1,4 +1,4 @@
-name: General issues
+name: Installation, packaging, dependencies
 description: Installation, packages, dependencies, "nothing works", test suite failures...
 title: "[Bug]: "
 labels: ["bug", "triage"]
@@ -9,6 +9,10 @@ body:
     attributes:
       value: |
         Thanks for taking the time to fill out this bug report!
+
+        If your issue involves using OCRmyPDF on specific file(s) and not getting
+        good results, this is the *wrong* issue template. Please use the recommended
+        template to ensure we have enough information to help.
   - type: textarea
     id: what-happened
     attributes:

.github/ISSUE_TEMPLATE/2-problem-with-specific-file.yml

@@ -32,7 +32,20 @@ body:
     attributes:
       label: Files
       description: Please attach the input and output files, or any screenshots that may be helpful.
-      placeholder: Drag and drop files here
+      placeholder: |
+        Drag and drop files here.
+
+        If you cannot provide a test file, we probably won't be able to help with the issue.
+        PDF is a complex file format, and there may be technical details in the PDF that are
+        causing the issue. There's really no substitute for a test file.
+
+        We understand files may contain personal or sensitive information. Here are some options:
+        - Try reproducing the issue with a file from the test suite. (See tests/resources)
+        - Try to create another file in the same way as your private file.
+        - Encrypt the file to OCRmyPDF's private GPG key.
+        - Use ``qpdf --json yourfile.pdf`` to produce a JSON representation of your file that
+          omits personal information.
+
   - type: dropdown
     id: packaging-system
     attributes:

.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
@@ -240,7 +241,7 @@ 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
@@ -257,7 +258,7 @@ jobs:
       # Required to create a release
       contents: write
     steps:
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4
         with:
           name: artifact
           path: dist

docs/release_notes.rst

@@ -30,8 +30,22 @@ OCRmyPDF typically supports the three most recent Python versions.
 
 .. |OCRmyPDF PyPI| image:: https://img.shields.io/pypi/v/ocrmypdf.svg
 
-v16.0.0rc1
-==========
+
+v16.0.2
+=======
+
+-  Temporarily changed PDF text renderer back to sandwich by default to address
+   regressions in macOS Preview.
+
+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",
-  "pluggy>=0.13.0",
+  "pikepdf>=8.10.1",
+  "pluggy>=1",
   "rich>=13",
 ]
 authors = [{ name = "James R. Barlow", email = "james@purplerock.ca" }]

src/ocrmypdf/builtin_plugins/tesseract_ocr.py

@@ -146,7 +146,7 @@ def check_options(options):
 
     # Decide on what renderer to use
     if options.pdf_renderer == 'auto':
-        options.pdf_renderer = 'hocr'
+        options.pdf_renderer = 'sandwich'
 
     if not tesseract.has_thresholding() and options.tesseract_thresholding != 0:
         log.warning(

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_space_bbox=debug,
+            render_paragraph_bbox=False,
+            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."""