modest improvement to cropping (safer)

tests/test_ink_detection.py

@@ -108,6 +108,14 @@ class InkDetectionTests(unittest.TestCase):
                     .7,(190,190,190),2)
         self.assertGreater(detect_bounds(image,dpi=150)['bottom_px'],1100)
 
+    def test_sparse_central_pencil_on_dark_grid_survives(self):
+        image = self.dark_grid()
+        # Thin, pale handwriting crossing the ruling is split into sparse
+        # components. Its central position distinguishes it from page holes.
+        cv2.putText(image,'result',(330,1090),cv2.FONT_HERSHEY_SCRIPT_SIMPLEX,
+                    .85,(155,155,155),1)
+        self.assertGreater(detect_bounds(image,dpi=150)['bottom_px'],1090)
+
     def test_large_unruled_diagram_is_not_paper(self):
         image = np.full((1200,850,3),255,np.uint8)
         cv2.rectangle(image,(100,100),(750,1100),(20,20,20),3)
@@ -151,6 +159,12 @@ class InkDetectionTests(unittest.TestCase):
                 r = detect_bounds(image,dpi=150)
                 self.assertGreater(r['bottom_px'],1060)
 
+    def test_faint_page_number_in_outer_band_does_not_block_crop(self):
+        image = self.dark_grid()
+        cv2.putText(image,'4/',(3,1160),cv2.FONT_HERSHEY_SIMPLEX,
+                    .55,(130,130,130),1)
+        self.assertLess(detect_bounds(image,dpi=150)['bottom_px'],850)
+
     def test_faded_neutral_grid(self):
         image = self.dark_grid()
         image[np.all(image == 65,axis=2)] = 145

tests/test_splitting_geometry.py

@@ -8,7 +8,10 @@ import numpy as np
 import pymupdf
 from pdf2image import convert_from_path
 
-from copienator.commands.splitting_int import _render_split_outputs
+from copienator.commands.splitting_int import (
+    ANSWER_TOP_PADDING_POINTS,
+    _render_split_outputs,
+)
 
 
 class SplittingGeometryTests(unittest.TestCase):
@@ -60,7 +63,8 @@ class SplittingGeometryTests(unittest.TestCase):
                             else:
                                 coordinates = [("A", 0, 250, 260, 0, 100),
                                                ("_", 0, 711, 721, 0, 100)]
-                                bounds = (bounds[0], max(bounds[1], height // 4),
+                                answer_top = int(height // 4 - ANSWER_TOP_PADDING_POINTS)
+                                bounds = (bounds[0], max(bounds[1], answer_top),
                                           bounds[2], min(bounds[3], height * 3 // 4))
                             _render_split_outputs(source, coordinates, root)
                             self.assert_matches_preview(root / "A.pdf", preview, bounds)
@@ -85,7 +89,7 @@ class SplittingGeometryTests(unittest.TestCase):
             rendered = convert_from_path(root / "A.pdf", dpi=72)
             self.assertEqual(len(rendered), 2)
             for actual, preview, bounds in zip(rendered, previews,
-                                               [(40, 700, 780, 920), (20, 80, 760, 250)]):
+                                               [(40, 688, 780, 920), (20, 80, 760, 250)]):
                 expected = np.asarray(preview.crop(bounds)).astype(float)
                 actual = np.asarray(actual).astype(float)
                 self.assertEqual(actual.shape, expected.shape)