Test and fix page box issues

2025-12-23 11:19:51 -08:00
parent 8d715c4157
commit eace567f7b
2 changed files with 132 additions and 4 deletions
@@ -0,0 +1,122 @@
+# SPDX-FileCopyrightText: 2025 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+from __future__ import annotations
+
+import pikepdf
+import pytest
+
+from .conftest import check_ocrmypdf
+
+page_rect = [0, 0, 612, 792]
+inset_rect = [200, 200, 612, 792]
+wh_rect = [0, 0, 412, 592]
+
+neg_rect = [-100, -100, 512, 692]
+
+mediabox_testdata = [
+    ('hocr', 'pdfa', 'ccitt.pdf', None, inset_rect, wh_rect),
+    ('sandwich', 'pdfa', 'ccitt.pdf', None, inset_rect, wh_rect),
+    ('hocr', 'pdf', 'ccitt.pdf', None, inset_rect, inset_rect),
+    ('sandwich', 'pdf', 'ccitt.pdf', None, inset_rect, inset_rect),
+    (
+        'hocr',
+        'pdfa',
+        'ccitt.pdf',
+        '--force-ocr',
+        inset_rect,
+        wh_rect,
+    ),
+    (
+        'hocr',
+        'pdf',
+        'ccitt.pdf',
+        '--force-ocr',
+        inset_rect,
+        wh_rect,
+    ),
+    ('hocr', 'pdfa', 'ccitt.pdf', '--force-ocr', neg_rect, page_rect),
+    ('hocr', 'pdf', 'ccitt.pdf', '--force-ocr', neg_rect, page_rect),
+]
+
+
+@pytest.mark.parametrize(
+    'renderer, output_type, in_pdf, mode, crop_to, crop_expected', mediabox_testdata
+)
+def test_media_box(
+    resources, outdir, renderer, output_type, in_pdf, mode, crop_to, crop_expected
+):
+    with pikepdf.open(resources / in_pdf) as pdf:
+        page = pdf.pages[0]
+        page.MediaBox = crop_to
+        pdf.save(outdir / 'cropped.pdf')
+    args = [
+        '--jobs',
+        '1',
+        '--pdf-renderer',
+        renderer,
+        '--output-type',
+        output_type,
+    ]
+    if mode:
+        args.append(mode)
+
+    check_ocrmypdf(outdir / 'cropped.pdf', outdir / 'processed.pdf', *args)
+
+    with pikepdf.open(outdir / 'processed.pdf') as pdf:
+        page = pdf.pages[0]
+        assert page.MediaBox == crop_expected
+
+
+cropbox_testdata = [
+    ('hocr', 'pdfa', 'ccitt.pdf', None, inset_rect, inset_rect),
+    ('sandwich', 'pdfa', 'ccitt.pdf', None, inset_rect, inset_rect),
+    ('hocr', 'pdf', 'ccitt.pdf', None, inset_rect, inset_rect),
+    ('sandwich', 'pdf', 'ccitt.pdf', None, inset_rect, inset_rect),
+    (
+        'hocr',
+        'pdfa',
+        'ccitt.pdf',
+        '--force-ocr',
+        inset_rect,
+        inset_rect,
+    ),
+    (
+        'hocr',
+        'pdf',
+        'ccitt.pdf',
+        '--force-ocr',
+        inset_rect,
+        inset_rect,
+    ),
+]
+
+
+@pytest.mark.parametrize(
+    'renderer, output_type, in_pdf, mode, crop_to, crop_expected', cropbox_testdata
+)
+def test_crop_box(
+    resources, outdir, renderer, output_type, in_pdf, mode, crop_to, crop_expected
+):
+    with pikepdf.open(resources / in_pdf) as pdf:
+        page = pdf.pages[0]
+        page.CropBox = crop_to
+        pdf.save(outdir / 'cropped.pdf')
+        pdf.save('cropped.pdf')
+    args = [
+        '--jobs',
+        '1',
+        '--pdf-renderer',
+        renderer,
+        '--output-type',
+        output_type,
+    ]
+    if mode:
+        args.append(mode)
+
+    check_ocrmypdf(outdir / 'cropped.pdf', outdir / 'processed.pdf', *args)
+
+    with pikepdf.open(outdir / 'processed.pdf') as pdf:
+        page = pdf.pages[0]
+        pdf.save('processed.pdf')
+        assert page.CropBox == crop_expected