menekis/OCRmyPDF
Public Access
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Also process art and bleed boxes

Browse Source
This commit is contained in:
James R. Barlow
2025-12-23 11:20:41 -08:00
parent eace567f7b
commit 4c1ef0b471
4 changed files with 101 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/ocrmypdf/_pipeline.py
+31 -10
View File
@@ -39,6 +39,7 @@ from ocrmypdf.hocrtransform import DebugRenderOptions, HocrTransform
from ocrmypdf.hocrtransform._font import Courier
from ocrmypdf.pdfa import generate_pdfa_ps
from ocrmypdf.pdfinfo import Colorspace, Encoding, PageInfo, PdfInfo
from ocrmypdf.pdfinfo.info import FloatRect
from ocrmypdf.pluginspec import OrientationConfidence
try:
@@ -832,6 +833,23 @@ def _offset_rect(rect: tuple[float, float, float, float], offset: tuple[float, f
)
def _adjust_pagebox(
page: pikepdf.Page,
media_box: FloatRect,
name: pikepdf.Name,
target_box: FloatRect,
offset: tuple[float, float],
swap_axis: bool,
):
if media_box == target_box:
return
box = _offset_rect(target_box, offset)
if swap_axis:
box = box[1], box[0], box[3], box[2]
page[name] = box
log.debug(f"{str(name)} = {target_box}")
def fix_pagepdf_boxes(
infile: Path | BinaryIO,
out_file: Path,
@@ -856,22 +874,25 @@ def fix_pagepdf_boxes(
"""
with pikepdf.open(infile) as pdf:
for page in pdf.pages:
# page.BleedBox = page_context.pageinfo.bleedbox
# page.ArtBox = page_context.pageinfo.artbox
log.debug(
f"initial mediabox={page.MediaBox} and pageinfo mediabox={page_context.pageinfo.mediabox}"
f"initial mediabox={page.MediaBox} and pageinfo "
f"mediabox={page_context.pageinfo.mediabox}"
)
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]
mediabox = mediabox[1], mediabox[0], mediabox[3], mediabox[2]
page.CropBox = cropbox
page.TrimBox = trimbox
log.debug(f"cropbox={cropbox}, trimbox={trimbox}, mediabox={mediabox}")
boxes = ['CropBox', 'TrimBox', 'ArtBox', 'BleedBox']
for box_name in boxes:
_adjust_pagebox(
page,
mediabox,
pikepdf.Name(f"/{box_name}"),
getattr(page_context.pageinfo, box_name.lower()),
offset,
swap_axis,
)
pdf.save(out_file)
return out_file
src/ocrmypdf/pdfinfo/info.py
+12 -2
View File
@@ -901,8 +901,8 @@ 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._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()]
@@ -1039,6 +1039,16 @@ class PageInfo:
"""Return trimbox of page in PDF coordinates."""
return self._trimbox
@property
def artbox(self) -> FloatRect:
"""Return artbox of page in PDF coordinates."""
return self._artbox
@property
def bleedbox(self) -> FloatRect:
"""Return bleedbox of page in PDF coordinates."""
return self._bleedbox
@property
def images(self) -> list[ImageInfo]:
"""Return images."""
tests/test_page_boxes.py
+2 -2
View File
@@ -102,7 +102,6 @@ def test_crop_box(
page = pdf.pages[0]
page.CropBox = crop_to
pdf.save(outdir / 'cropped.pdf')
pdf.save('cropped.pdf')
args = [
'--jobs',
'1',
@@ -110,6 +109,8 @@ def test_crop_box(
renderer,
'--output-type',
output_type,
'--optimize',
'0',
]
if mode:
args.append(mode)
@@ -118,5 +119,4 @@ def test_crop_box(
with pikepdf.open(outdir / 'processed.pdf') as pdf:
page = pdf.pages[0]
pdf.save('processed.pdf')
assert page.CropBox == crop_expected
tests/test_rotation.py
+56 -9
View File
@@ -51,20 +51,27 @@ def compare_images_monochrome(
with Image.open(reference_png) as reference_im, Image.open(test_png) as test_im:
assert reference_im.mode == test_im.mode == '1'
difference = ImageChops.logical_xor(reference_im, test_im)
assert difference.mode == '1'
# Pillow uses black is 0 for '1'. Invert so that foreground is 1, then
# compare
inv_ref_im = ImageChops.invert(reference_im)
inv_test_im = ImageChops.invert(test_im)
foreground_match = ImageChops.logical_and(inv_ref_im, inv_test_im)
foreground_total = ImageChops.logical_or(inv_ref_im, inv_test_im)
assert foreground_match.mode == '1'
histogram = difference.histogram()
histogram = foreground_match.histogram()
histogram_total = foreground_total.histogram()
assert (
len(histogram) == 256
), "Expected Pillow to convert to grayscale for histogram"
# All entries other than first and last will be 0
count_same = histogram[0]
count_different = histogram[-1]
total = count_same + count_different
return count_same / (total)
# count_same = histogram[0]
# count_different = histogram[-1]
# total = count_same + count_different
# print(f"{count_same / (total)}")
# return count_same / (total)
return histogram[-1] / (histogram_total[-1] + 1)
def test_monochrome_comparison(resources, outdir):
@@ -211,7 +218,7 @@ def test_rotate_deskew_ocr_timeout(resources, outdir):
assert cmp > 0.95
def make_rotate_test(imagefile, outdir, prefix, image_angle, page_angle):
def make_rotate_test(imagefile, outdir, prefix, image_angle, page_angle, cropbox=None):
memimg = BytesIO()
with Image.open(fspath(imagefile)) as im:
if image_angle != 0:
@@ -230,6 +237,8 @@ def make_rotate_test(imagefile, outdir, prefix, image_angle, page_angle):
with pikepdf.open(mempdf) as pdf:
pdf.pages[0].Rotate = page_angle
target = outdir / f'{prefix}_{image_angle}_{page_angle}.pdf'
if cropbox:
pdf.pages[0].CropBox = cropbox
pdf.save(target)
return target
@@ -284,6 +293,44 @@ def test_page_rotate_tag(page_rotate_angle, resources, outdir, caplog):
assert 'is a' in test_text, test_text
@pytest.mark.parametrize('page_rotate_angle', (0, 90, 180, 270))
@pytest.mark.parametrize('renderer', ['sandwich', 'hocr'])
@pytest.mark.parametrize('output_type', ['pdf', 'pdfa'])
def test_rotate_and_crop(
resources, outdir, page_rotate_angle, renderer, output_type, caplog
):
cropbox = (100, 200, 1000, 800)
reference = make_rotate_test(
resources / 'typewriter.png', outdir, 'ref', 0, 0, cropbox
)
test = make_rotate_test(
resources / 'typewriter.png',
outdir,
'test',
-page_rotate_angle,
page_rotate_angle,
cropbox,
)
out = test.with_suffix('.out.pdf')
exitcode = run_ocrmypdf_api(
test,
out,
'-O0',
'--rotate-pages',
'--rotate-pages-threshold',
'0',
'--pdf-renderer',
renderer,
'--output-type',
output_type,
'--no-progress-bar',
)
assert exitcode == 0, caplog.text
assert compare_images_monochrome(outdir, reference, 1, out, 1) > 0.9
def test_rasterize_rotates(resources, tmp_path):
pm = get_plugin_manager([])