Attempt to deal with oddball mediaboxes

src/ocrmypdf/_pipeline.py

@@ -718,9 +718,8 @@ def create_pdf_page_from_image(
     if swap_axis:
         pagesize = pagesize[1], pagesize[0]
 
+    # Create a new single page PDF to hold
     bio = BytesIO()
-
-    # This create a single page PDF
     with open(image, 'rb') as imfile:
         log.debug('convert')
 
@@ -795,19 +794,47 @@ def ocr_engine_textonly_pdf(
     return output_pdf, output_text
 
 
+def _offset_rect(rect: tuple[float, float, float, float], offset: tuple[float, float]):
+    """Offset a rectangle by a given amount."""
+    return (
+        rect[0] + offset[0],
+        rect[1] + offset[1],
+        rect[2] + offset[0],
+        rect[3] + offset[1],
+    )
+
+
 def fix_pagepdf_boxes(
     infile: Path | BinaryIO,
     out_file: Path,
     page_context: PageContext,
     swap_axis: bool = False,
 ) -> Path:
-    """Fix the bounding boxes in a single page PDF."""
+    """Fix the bounding boxes in a single page PDF.
+
+    The single page PDF is created with a normal MediaBox with its lower left corner
+    at (0, 0). infile is the single page PDF. page_context.mediabox has the original
+    file's mediabox, which may have a different origin. We needto adjust the other
+    boxes in the single page PDF to match the effect they had on the original page.
+
+    When correcting page rotation, we create a single page PDF that is correctly
+    rotated instead of an incorrectly rotated and then setting page.Rotate on it.
+    If rotation is either 90 or 270 degrees, then this function can be called
+    with swap_axis to swap the X and Y coordinates of all the boxes.
+
+    We are not concerned with solving degenerate cases where the boxes overlap or
+    or express invalid rectangles. We merely pass the boxes, producing a
+    transformation equivalent to the change made by constructing a new page image.
+    """
     with pikepdf.open(infile) as pdf:
         for page in pdf.pages:
             # page.BleedBox = page_context.pageinfo.bleedbox
             # page.ArtBox = page_context.pageinfo.artbox
-            cropbox = page_context.pageinfo.cropbox
-            trimbox = page_context.pageinfo.trimbox
+            mediabox = page_context.pageinfo.mediabox
+            offset = mediabox[0], mediabox[1]
+            cropbox = _offset_rect(page_context.pageinfo.cropbox, offset)
+            trimbox = _offset_rect(page_context.pageinfo.trimbox, offset)
+
             if swap_axis:
                 cropbox = cropbox[1], cropbox[0], cropbox[3], cropbox[2]
                 trimbox = trimbox[1], trimbox[0], trimbox[3], trimbox[2]

src/ocrmypdf/_pipelines/ocr.py

@@ -22,7 +22,6 @@ from ocrmypdf._graft import OcrGrafter
 from ocrmypdf._jobcontext import PageContext, PdfContext
 from ocrmypdf._pipeline import (
     copy_final,
-    fix_pagepdf_boxes,
     get_pdfinfo,
     is_ocr_required,
     merge_sidecars,
@@ -81,9 +80,6 @@ def _exec_page_sync(page_context: PageContext) -> PageResult:
         page_context
     )
     ocr_out, text_out = _image_to_ocr_text(page_context, ocr_image_out)
-
-    # fix_pagepdf_boxes(ocr_out, page_context)
-
     return PageResult(
         pageno=page_context.pageno,
         pdf_page_from_image=pdf_page_from_image_out,

src/ocrmypdf/helpers.py

@@ -26,6 +26,7 @@ from typing import (
 
 import img2pdf
 import pikepdf
+from deprecation import deprecated
 
 log = logging.getLogger(__name__)
 
@@ -136,6 +137,7 @@ class Resolution(Generic[T]):
         return self._isclose(self.x, other.x) and self._isclose(self.y, other.y)
 
 
+@deprecated(deprecated_in='15.4.0')
 class NeverRaise(Exception):
     """An exception that is never raised."""
 

src/ocrmypdf/pdfinfo/info.py

@@ -857,6 +857,7 @@ class PageInfo:
         # self._artbox = [float(d) for d in page.artbox.as_list()]
         # self._bleedbox = [float(d) for d in page.bleedbox.as_list()]
         self._cropbox = [float(d) for d in page.cropbox.as_list()]
+        self._mediabox = [float(d) for d in page.mediabox.as_list()]
         self._trimbox = [float(d) for d in page.trimbox.as_list()]
 
         check_this_page = pageno in check_pages
@@ -977,9 +978,14 @@ class PageInfo:
 
     @property
     def cropbox(self) -> FloatRect:
-        """Return trimbox of page in PDF coordinates."""
+        """Return cropbox of page in PDF coordinates."""
         return self._cropbox
 
+    @property
+    def mediabox(self) -> FloatRect:
+        """Return mediabox of page in PDF coordinates."""
+        return self._mediabox
+
     @property
     def trimbox(self) -> FloatRect:
         """Return trimbox of page in PDF coordinates."""