Repair fix coords

ocrd_segment/repair.py

@@ -6,7 +6,7 @@
 from scipy.ndimage import filters, morphology
 import cv2
 import numpy as np
-from shapely.geometry import Polygon, LineString
+from shapely.geometry import asPolygon, Polygon, LineString
 
 from ocrd import Processor
 from ocrd_utils import (
@@ -240,11 +240,13 @@ def sanitize_page(self, page, page_id):
                     LOG.warning('Ignoring contour %d too small (%d/%d) in region "%s"',
                                 i, area, total_area, region.id)
                     continue
-                # simplify shape:
+                # simplify shape (until valid):
                 # can produce invalid (self-intersecting) polygons:
                 #polygon = cv2.approxPolyDP(contour, 2, False)[:, 0, ::] # already ordered x,y
                 polygon = contour[:, 0, ::] # already ordered x,y
-                polygon = Polygon(polygon).simplify(1).exterior.coords
+                polygon = Polygon(polygon).simplify(1)
+                polygon = make_valid(polygon)
+                polygon = polygon.exterior.coords[:-1] # keep open
                 if len(polygon) < 4:
                     LOG.warning('Ignoring contour %d less than 4 points in region "%s"',
                                 i, region.id)
@@ -354,7 +356,13 @@ def _plausibilize_group(regionspolys, rogroup, mark_for_deletion, mark_for_mergi
                 # and use-cases in the future
                 superpoly = Polygon(polygon_from_points(superreg.get_Coords().points))
                 superpoly = superpoly.union(poly)
-                superreg.get_Coords().points = points_from_polygon(superpoly.exterior.coords)
+                if superpoly.type == 'MultiPolygon':
+                    superpoly = superpoly.convex_hull
+                if superpoly.minimum_clearance < 1.0:
+                    superpoly = asPolygon(np.round(superpoly.exterior.coords))
+                superpoly = make_valid(superpoly)
+                superpoly = superpoly.exterior.coords[:-1] # keep open
+                superreg.get_Coords().points = points_from_polygon(superpoly)
                 # FIXME should we merge/mix attributes and features?
                 if region.get_orientation() != superreg.get_orientation():
                     LOG.warning('Merging region "%s" with orientation %f into "%s" with %f',
@@ -399,3 +407,18 @@ def _plausibilize_group(regionspolys, rogroup, mark_for_deletion, mark_for_mergi
         if region.parent_object_:
             # remove in-place
             region.parent_object_.get_TextRegion().remove(region)
+
+def make_valid(polygon):
+    """Ensures shapely.geometry.Polygon object is valid by repeated simplification"""
+    for split in range(1, len(polygon.exterior.coords)-1):
+        if polygon.is_valid or polygon.simplify(polygon.area).is_valid:
+            break
+        # simplification may not be possible (at all) due to ordering
+        # in that case, try another starting point
+        polygon = Polygon(polygon.exterior.coords[-split:]+polygon.exterior.coords[:-split])
+    for tolerance in range(1, int(polygon.area)):
+        if polygon.is_valid:
+            break
+        # simplification may require a larger tolerance
+        polygon = polygon.simplify(tolerance)
+    return polygon

requirements.txt

@@ -1,4 +1,4 @@
 ocrd >= 2.13.1
-shapely
+shapely >= 1.7.1
 scikit-image
 numpy