From eace567f7bfc82d70d7b4771cb1ea7874761bb48 Mon Sep 17 00:00:00 2001
From: "James R. Barlow" <james@purplerock.ca>
Date: Tue, 11 Feb 2025 00:40:01 -0800
Subject: [PATCH] Test and fix page box issues

---
 src/ocrmypdf/_pipeline.py |  14 +++--
 tests/test_page_boxes.py  | 122 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 132 insertions(+), 4 deletions(-)
 create mode 100644 tests/test_page_boxes.py

diff --git a/src/ocrmypdf/_pipeline.py b/src/ocrmypdf/_pipeline.py
index 90524d58..3eab75f9 100644
--- a/src/ocrmypdf/_pipeline.py
+++ b/src/ocrmypdf/_pipeline.py
@@ -549,7 +549,9 @@ def rasterize(
 
     device = colorspaces[device_idx]
 
-    log.debug(f"Rasterize with {device}, rotation {correction}")
+    log.debug(
+        f"Rasterize with {device}, rotation {correction}, mediabox {pageinfo.mediabox}"
+    )
 
     canvas_dpi, page_dpi = calculate_raster_dpi(page_context)
 
@@ -840,7 +842,7 @@ def fix_pagepdf_boxes(
 
     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
+    file's mediabox, which may have a different origin. We need to 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
@@ -856,16 +858,20 @@ def fix_pagepdf_boxes(
         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}"
+            )
             mediabox = page_context.pageinfo.mediabox
-            offset = mediabox[0], mediabox[1]
+            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}")
         pdf.save(out_file)
     return out_file
 
diff --git a/tests/test_page_boxes.py b/tests/test_page_boxes.py
new file mode 100644
index 00000000..cc3386b1
--- /dev/null
+++ b/tests/test_page_boxes.py
@@ -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