Repair fix coords

.pylintrc

@@ -3,6 +3,8 @@ ignored-modules=cv2
 
 [MESSAGES CONTROL]
 disable =
+    super-with-arguments,
+    trailing-whitespace,
     missing-docstring,
     no-self-use,
     superfluous-parens,

CHANGELOG.md

@@ -4,6 +4,17 @@ Versioned according to [Semantic Versioning](http://semver.org/).
 
 ## Unreleased
 
+## [0.1.1] - 2020-09-14
+
+Changed:
+
+  * repair: traverse all text regions recursively
+
+Fixed:
+
+  * repair: be robust against invalid input polygons
+  * repair: be careful to make valid output polygons
+
 ## [0.1.0] - 2020-08-21
 
 Changed:

ocrd_segment/extract_lines.py

@@ -11,10 +11,6 @@
     polygon_from_points,
     MIME_TO_EXT
 )
-from ocrd_models.ocrd_page import (
-    LabelsType, LabelType,
-    MetadataItemType
-)
 from ocrd_modelfactory import page_from_file
 from ocrd import Processor
 
@@ -75,18 +71,8 @@ def process(self):
             page_id = input_file.pageId or input_file.ID
             LOG.info("INPUT FILE %i / %s", n, page_id)
             pcgts = page_from_file(self.workspace.download_file(input_file))
+            self.add_metadata(pcgts)
             page = pcgts.get_Page()
-            metadata = pcgts.get_Metadata() # ensured by from_file()
-            metadata.add_MetadataItem(
-                MetadataItemType(type_="processingStep",
-                                 name=self.ocrd_tool['steps'][0],
-                                 value=TOOL,
-                                 Labels=[LabelsType(
-                                     externalModel="ocrd-tool",
-                                     externalId="parameters",
-                                     Label=[LabelType(type_=name,
-                                                      value=self.parameter[name])
-                                            for name in self.parameter.keys()])]))
             page_image, page_coords, page_image_info = self.workspace.image_from_page(
                 page, page_id,
                 transparency=self.parameter['transparency'])

ocrd_segment/extract_pages.py

@@ -16,10 +16,6 @@
     xywh_from_polygon,
     MIME_TO_EXT
 )
-from ocrd_models.ocrd_page import (
-    LabelsType, LabelType,
-    MetadataItemType
-)
 from ocrd_modelfactory import page_from_file
 from ocrd import Processor
 
@@ -168,19 +164,9 @@ def process(self):
             num_page_id = int(page_id.strip(page_id.strip("0123456789")))
             LOG.info("INPUT FILE %i / %s", n, page_id)
             pcgts = page_from_file(self.workspace.download_file(input_file))
+            self.add_metadata(pcgts)
             page = pcgts.get_Page()
             ptype = page.get_type()
-            metadata = pcgts.get_Metadata() # ensured by from_file()
-            metadata.add_MetadataItem(
-                MetadataItemType(type_="processingStep",
-                                 name=self.ocrd_tool['steps'][0],
-                                 value=TOOL,
-                                 Labels=[LabelsType(
-                                     externalModel="ocrd-tool",
-                                     externalId="parameters",
-                                     Label=[LabelType(type_=name,
-                                                      value=self.parameter[name])
-                                            for name in self.parameter])]))
             page_image, page_coords, page_image_info = self.workspace.image_from_page(
                 page, page_id,
                 feature_filter='binarized',

ocrd_segment/extract_regions.py

@@ -10,10 +10,6 @@
     polygon_from_points,
     MIME_TO_EXT
 )
-from ocrd_models.ocrd_page import (
-    LabelsType, LabelType,
-    MetadataItemType
-)
 from ocrd_modelfactory import page_from_file
 from ocrd import Processor
 
@@ -72,18 +68,8 @@ def process(self):
             page_id = input_file.pageId or input_file.ID
             LOG.info("INPUT FILE %i / %s", n, page_id)
             pcgts = page_from_file(self.workspace.download_file(input_file))
+            self.add_metadata(pcgts)
             page = pcgts.get_Page()
-            metadata = pcgts.get_Metadata() # ensured by from_file()
-            metadata.add_MetadataItem(
-                MetadataItemType(type_="processingStep",
-                                 name=self.ocrd_tool['steps'][0],
-                                 value=TOOL,
-                                 Labels=[LabelsType(
-                                     externalModel="ocrd-tool",
-                                     externalId="parameters",
-                                     Label=[LabelType(type_=name,
-                                                      value=self.parameter[name])
-                                            for name in self.parameter])]))
             page_image, page_coords, page_image_info = self.workspace.image_from_page(
                 page, page_id,
                 transparency=self.parameter['transparency'])

ocrd_segment/import_coco_segmentation.py

@@ -17,8 +17,6 @@
 # pragma pylint: disable=unused-import
 # (region types will be referenced indirectly via globals())
 from ocrd_models.ocrd_page import (
-    MetadataItemType,
-    LabelsType, LabelType,
     CoordsType,
     TextRegionType,
     ImageRegionType,
@@ -138,21 +136,9 @@ def process(self):
             num_page_id = int(page_id.strip(page_id.strip("0123456789")))
             LOG.info("INPUT FILE %i / %s", n, page_id)
             pcgts = page_from_file(self.workspace.download_file(input_file))
+            self.add_metadata(pcgts)
             page = pcgts.get_Page()
 
-            # add metadata about this operation and its runtime parameters:
-            metadata = pcgts.get_Metadata() # ensured by from_file()
-            metadata.add_MetadataItem(
-                MetadataItemType(type_="processingStep",
-                                 name=self.ocrd_tool['steps'][0],
-                                 value=TOOL,
-                                 Labels=[LabelsType(
-                                     externalModel="ocrd-tool",
-                                     externalId="parameters",
-                                     Label=[LabelType(type_=name,
-                                                      value=self.parameter[name])
-                                            for name in self.parameter.keys()])]))
-
             # find COCO image
             if page.imageFilename in images_by_filename:
                 image = images_by_filename[page.imageFilename]

ocrd_segment/import_image_segmentation.py

@@ -18,8 +18,6 @@
 # pragma pylint: disable=unused-import
 # (region types will be referenced indirectly via globals())
 from ocrd_models.ocrd_page import (
-    MetadataItemType,
-    LabelsType, LabelType,
     CoordsType,
     TextRegionType,
     ImageRegionType,
@@ -89,21 +87,9 @@ def process(self):
             input_file, segmentation_file = ift
             LOG.info("processing page %s", input_file.pageId)
             pcgts = page_from_file(self.workspace.download_file(input_file))
+            self.add_metadata(pcgts)
             page = pcgts.get_Page()
 
-            # add metadata about this operation and its runtime parameters:
-            metadata = pcgts.get_Metadata() # ensured by from_file()
-            metadata.add_MetadataItem(
-                MetadataItemType(type_="processingStep",
-                                 name=self.ocrd_tool['steps'][0],
-                                 value=TOOL,
-                                 Labels=[LabelsType(
-                                     externalModel="ocrd-tool",
-                                     externalId="parameters",
-                                     Label=[LabelType(type_=name,
-                                                      value=self.parameter[name])
-                                            for name in self.parameter.keys()])]))
-
             # import mask image
             segmentation_filename = self.workspace.download_file(segmentation_file).local_filename
             with pushd_popd(self.workspace.directory):

ocrd_segment/ocrd-tool.json

@@ -1,5 +1,5 @@
 {
-  "version": "0.1.0",
+  "version": "0.1.1",
   "git_url": "https://github.com/OCR-D/ocrd_segment",
   "tools": {
     "ocrd-segment-repair": {