Merge branch 'feature/pageboxes'

docs/api.rst

@@ -112,7 +112,9 @@ OCRmyPDF is strict about not writing to standard output so that
 users can safely use it in a pipeline and produce a valid output
 file. A caller application will have to ensure it does not write to
 standard output either, if it wants to be compatible with this
-behavior and support piping to a file.
+behavior and support piping to a file. Another benefit of running
+OCRmyPDF in a child process, as recommended above, is that it will
+not interfere with the parent process's standard output.
 
 Exceptions
 ----------

pyproject.toml

@@ -131,7 +131,10 @@ norecursedirs = ["lib", ".pc", ".git", "venv", "output", "cache", "resources"]
 testpaths = ["tests"]
 addopts = "-n auto"
 markers = ["slow"]
-filterwarnings = ["ignore:.*XMLParser.*:DeprecationWarning"]
+filterwarnings = [
+  "ignore:.*XMLParser.*:DeprecationWarning",
+  'ignore:.*ast.NameConstant.*:DeprecationWarning',
+]
 
 [tool.mypy]
 

src/ocrmypdf/_graft.py

@@ -289,9 +289,8 @@ class OcrGrafter:
 
             # Translate the text so it is centered at (0, 0), rotate it there, adjust
             # for a size different between initial and text PDF, then untranslate, and
-            # finally move the lower left corner to match the mediabox. All transforms
-            # must be premultiplied so they are applied in reverse order here.
-            ctm = corner @ untranslate @ scale @ rotate @ translate
+            # finally move the lower left corner to match the mediabox.
+            ctm = translate @ rotate @ scale @ untranslate @ corner
             log.debug("Grafting with ctm %r", ctm)
 
             base_resources = _ensure_dictionary(base_page.obj, Name.Resources)

src/ocrmypdf/_pipeline.py

@@ -12,6 +12,7 @@ import re
 import sys
 from collections.abc import Iterable, Iterator, Sequence
 from contextlib import suppress
+from io import BytesIO
 from pathlib import Path
 from shutil import copyfileobj, copystat
 from typing import Any, BinaryIO, TypeVar, cast
@@ -713,19 +714,29 @@ def create_pdf_page_from_image(
     pageinfo = page_context.pageinfo
     pagesize = 72.0 * float(pageinfo.width_inches), 72.0 * float(pageinfo.height_inches)
     effective_rotation = (pageinfo.rotation - orientation_correction) % 360
-    if effective_rotation % 180 == 90:
+    swap_axis = effective_rotation % 180 == 90
+    if swap_axis:
         pagesize = pagesize[1], pagesize[0]
 
-    # This create a single page PDF
-    with open(image, 'rb') as imfile, open(output_file, 'wb') as pdf:
+    # Create a new single page PDF to hold
+    bio = BytesIO()
+    with open(image, 'rb') as imfile:
         log.debug('convert')
 
         layout_fun = img2pdf.get_layout_fun(pagesize)
         img2pdf.convert(
-            imfile, layout_fun=layout_fun, outputstream=pdf, **IMG2PDF_KWARGS
+            imfile,
+            layout_fun=layout_fun,
+            outputstream=bio,
+            engine=img2pdf.Engine.pikepdf,
+            rotation=img2pdf.Rotation.ifvalid,
         )
         log.debug('convert done')
 
+    # img2pdf does not generate boxes correctly, so we fix them
+    bio.seek(0)
+    fix_pagepdf_boxes(bio, output_file, page_context, swap_axis=swap_axis)
+
     output_file = page_context.plugin_manager.hook.filter_pdf_page(
         page=page_context, image_filename=image, output_pdf=output_file
     )
@@ -780,7 +791,57 @@ def ocr_engine_textonly_pdf(
         output_text=output_text,
         options=options,
     )
-    return (output_pdf, output_text)
+    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.
+
+    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
+            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]
+            page.CropBox = cropbox
+            page.TrimBox = trimbox
+        pdf.save(out_file)
+    return pdf
 
 
 def generate_postscript_stub(context: PdfContext) -> Path:

src/ocrmypdf/_pipelines/ocr.py

@@ -80,7 +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)
-
     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

@@ -854,6 +854,12 @@ class PageInfo:
         width_pt = mediabox[2] - mediabox[0]
         height_pt = mediabox[3] - mediabox[1]
 
+        # 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
 
         if check_this_page and detailed_analysis:
@@ -970,6 +976,21 @@ class PageInfo:
         else:
             raise ValueError("rotation must be a cardinal angle")
 
+    @property
+    def cropbox(self) -> FloatRect:
+        """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."""
+        return self._trimbox
+
     @property
     def images(self) -> list[ImageInfo]:
         """Return images."""

tests/test_optimize.py

@@ -176,9 +176,10 @@ def test_multiple_pngs(resources, outdir):
         )
         mock.assert_called()
 
-    with pikepdf.open(outdir / 'in.pdf') as inpdf, pikepdf.open(
-        outdir / 'out.pdf'
-    ) as outpdf:
+    with (
+        pikepdf.open(outdir / 'in.pdf') as inpdf,
+        pikepdf.open(outdir / 'out.pdf') as outpdf,
+    ):
         for n in range(len(inpdf.pages)):
             inim = next(iter(inpdf.pages[n].images.values()))
             outim = next(iter(outpdf.pages[n].images.values()))

tests/test_rotation.py

@@ -4,10 +4,10 @@
 from __future__ import annotations
 
 import operator
-import warnings
 from io import BytesIO
 from math import cos, pi, sin
 from os import fspath
+from subprocess import run
 
 import img2pdf
 import pikepdf
@@ -22,10 +22,6 @@ from ocrmypdf.pdfinfo import PdfInfo
 
 from .conftest import check_ocrmypdf, run_ocrmypdf_api
 
-warnings.filterwarnings(
-    "ignore", category=DeprecationWarning, module="reportlab.lib.rl_safe_eval"
-)
-
 # pylintx: disable=unused-variable
 
 RENDERERS = ['hocr', 'sandwich']
@@ -215,34 +211,35 @@ def test_rotate_deskew_ocr_timeout(resources, outdir):
     assert cmp > 0.95
 
 
+def make_rotate_test(imagefile, outdir, prefix, image_angle, page_angle):
+    memimg = BytesIO()
+    with Image.open(fspath(imagefile)) as im:
+        if image_angle != 0:
+            ccw_angle = -image_angle % 360
+            im = im.transpose(getattr(Image.Transpose, f'ROTATE_{ccw_angle}'))
+        im.save(memimg, format='PNG')
+    memimg.seek(0)
+    mempdf = BytesIO()
+    img2pdf.convert(
+        memimg.read(),
+        layout_fun=img2pdf.get_fixed_dpi_layout_fun((200, 200)),
+        outputstream=mempdf,
+        **IMG2PDF_KWARGS,
+    )
+    mempdf.seek(0)
+    with pikepdf.open(mempdf) as pdf:
+        pdf.pages[0].Rotate = page_angle
+        target = outdir / f'{prefix}_{image_angle}_{page_angle}.pdf'
+        pdf.save(target)
+        return target
+
+
 @pytest.mark.slow
 @pytest.mark.parametrize('page_angle', (0, 90, 180, 270))
 @pytest.mark.parametrize('image_angle', (0, 90, 180, 270))
 def test_rotate_page_level(image_angle, page_angle, resources, outdir, caplog):
-    def make_rotate_test(prefix, image_angle, page_angle):
-        memimg = BytesIO()
-        with Image.open(fspath(resources / 'typewriter.png')) as im:
-            if image_angle != 0:
-                ccw_angle = -image_angle % 360
-                im = im.transpose(getattr(Image.Transpose, f'ROTATE_{ccw_angle}'))
-            im.save(memimg, format='PNG')
-        memimg.seek(0)
-        mempdf = BytesIO()
-        img2pdf.convert(
-            memimg.read(),
-            layout_fun=img2pdf.get_fixed_dpi_layout_fun((200, 200)),
-            outputstream=mempdf,
-            **IMG2PDF_KWARGS,
-        )
-        mempdf.seek(0)
-        with pikepdf.open(mempdf) as pdf:
-            pdf.pages[0].Rotate = page_angle
-            target = outdir / f'{prefix}_{image_angle}_{page_angle}.pdf'
-            pdf.save(target)
-            return target
-
-    reference = make_rotate_test('ref', 0, 0)
-    test = make_rotate_test('test', image_angle, page_angle)
+    reference = make_rotate_test(resources / 'typewriter.png', outdir, 'ref', 0, 0)
+    test = make_rotate_test(resources, outdir, 'test', image_angle, page_angle)
     out = test.with_suffix('.out.pdf')
 
     exitcode = run_ocrmypdf_api(
@@ -258,6 +255,33 @@ def test_rotate_page_level(image_angle, page_angle, resources, outdir, caplog):
     assert compare_images_monochrome(outdir, reference, 1, out, 1) > 0.2
 
 
+@pytest.mark.slow
+@pytest.mark.parametrize('page_rotate_angle', (0, 90, 180, 270))
+def test_page_rotate_tag(page_rotate_angle, resources, outdir, caplog):
+    # Check that pages that have an image that is misrotated but restored to
+    # correct rotation with a /Rotate will be processed correct and yield text.
+    test = make_rotate_test(
+        resources / 'crom.png', outdir, 'test', -page_rotate_angle, page_rotate_angle
+    )
+    out = test.with_suffix('.out.pdf')
+    exitcode = run_ocrmypdf_api(
+        test,
+        out,
+        '-O0',
+    )
+    assert exitcode == 0, caplog.text
+
+    def pdftotext(filename):
+        return (
+            run(['pdftotext', '-enc', 'UTF-8', filename, '-'], capture_output=True)
+            .stdout.strip()
+            .decode('utf-8')
+        )
+
+    test_text = pdftotext(out)
+    assert 'is a' in test_text, test_text
+
+
 def test_rasterize_rotates(resources, tmp_path):
     pm = get_plugin_manager([])