ocropy processors: rebase on new core (recursive region enumerator, add_metadata)

Author: Robert Sachunsky

ocrd_cis/ocrd-tool.json

@@ -61,7 +61,7 @@
 				},
 				"level-of-operation": {
 					"type": "string",
-					"enum": ["page", "region", "line"],
+					"enum": ["page", "table", "region", "line"],
 					"description": "PAGE XML hierarchy level granularity to annotate images for",
 					"default": "page"
 				}
@@ -92,7 +92,7 @@
 				},
 				"level-of-operation": {
 					"type": "string",
-					"enum": ["page", "region"],
+					"enum": ["page", "table", "region"],
 					"description": "PAGE XML hierarchy level granularity to annotate images for",
 					"default": "region"
 				}

ocrd_cis/ocropy/binarize.py

@@ -15,8 +15,6 @@
 )
 from ocrd_modelfactory import page_from_file
 from ocrd_models.ocrd_page import (
-    MetadataItemType,
-    LabelsType, LabelType,
     to_xml, AlternativeImageType
 )
 from ocrd import Processor
@@ -118,21 +116,9 @@ def process(self):
             file_id = make_file_id(input_file, self.output_file_grp)
 
             pcgts = page_from_file(self.workspace.download_file(input_file))
+            self.add_metadata(pcgts)
             page_id = pcgts.pcGtsId or input_file.pageId or input_file.ID # (PageType has no id)
             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()])]))
 
             page_image, page_xywh, page_image_info = self.workspace.image_from_page(
                 page, page_id, feature_filter='binarized')
@@ -151,8 +137,10 @@ def process(self):
                 self.process_page(page, page_image, page_xywh, zoom,
                                   input_file.pageId, file_id)
             else:
-                regions = page.get_TextRegion() + (
-                    page.get_TableRegion() if level == 'region' else [])
+                if level == 'table':
+                    regions = page.get_TableRegion()
+                else: # region
+                    regions = page.get_AllRegions(classes=['Text'])
                 if not regions:
                     self.logger.warning('Page "%s" contains no text regions', page_id)
                 for region in regions:

ocrd_cis/ocropy/clip.py

@@ -9,8 +9,6 @@
 
 from ocrd_modelfactory import page_from_file
 from ocrd_models.ocrd_page import (
-    MetadataItemType,
-    LabelsType, LabelType,
     to_xml, AlternativeImageType
 )
 from ocrd import Processor
@@ -89,22 +87,10 @@ def process(self):
             file_id = make_file_id(input_file, self.output_file_grp)
 
             pcgts = page_from_file(self.workspace.download_file(input_file))
+            self.add_metadata(pcgts)
             page_id = pcgts.pcGtsId or input_file.pageId or input_file.ID # (PageType has no id)
             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()])]))
-            
             page_image, page_coords, page_image_info = self.workspace.image_from_page(
                 page, page_id, feature_selector='binarized')
             if self.parameter['dpi'] > 0:

ocrd_cis/ocropy/denoise.py

@@ -10,8 +10,6 @@
 )
 from ocrd_modelfactory import page_from_file
 from ocrd_models.ocrd_page import (
-    MetadataItemType,
-    LabelsType, LabelType,
     to_xml, AlternativeImageType
 )
 from ocrd import Processor
@@ -62,21 +60,9 @@ def process(self):
             file_id = make_file_id(input_file, self.output_file_grp)
 
             pcgts = page_from_file(self.workspace.download_file(input_file))
+            self.add_metadata(pcgts)
             page_id = pcgts.pcGtsId or input_file.pageId or input_file.ID # (PageType has no id)
             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()])]))
 
             page_image, page_xywh, page_image_info = self.workspace.image_from_page(
                 page, page_id,
@@ -96,8 +82,7 @@ def process(self):
                 self.process_segment(page, page_image, page_xywh, zoom,
                                      input_file.pageId, file_id)
             else:
-                regions = page.get_TextRegion() + (
-                    page.get_TableRegion() if level == 'region' else [])
+                regions = page.get_AllRegions(classes=['Text'])
                 if not regions:
                     LOG.warning('Page "%s" contains no text regions', page_id)
                 for region in regions:

ocrd_cis/ocropy/deskew.py

@@ -11,8 +11,6 @@
 )
 from ocrd_modelfactory import page_from_file
 from ocrd_models.ocrd_page import (
-    MetadataItemType,
-    LabelsType, LabelType,
     to_xml, AlternativeImageType
 )
 from ocrd import Processor
@@ -68,21 +66,9 @@ def process(self):
             file_id = make_file_id(input_file, self.output_file_grp)
 
             pcgts = page_from_file(self.workspace.download_file(input_file))
+            self.add_metadata(pcgts)
             page_id = pcgts.pcGtsId or input_file.pageId or input_file.ID # (PageType has no id)
             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()])]))
 
             page_image, page_coords, _ = self.workspace.image_from_page(
                 page, page_id,
@@ -95,7 +81,10 @@ def process(self):
                                       "page '%s'" % page_id, input_file.pageId,
                                       file_id)
             else:
-                regions = page.get_TextRegion()
+                if level == 'table':
+                    regions = page.get_TableRegion()
+                else: # region
+                    regions = page.get_AllRegions(classes=['Text'])
                 if not regions:
                     LOG.warning('Page "%s" contains no text regions', page_id)
                 for region in regions:

ocrd_cis/ocropy/dewarp.py

@@ -10,8 +10,6 @@
 )
 from ocrd_modelfactory import page_from_file
 from ocrd_models.ocrd_page import (
-    MetadataItemType,
-    LabelsType, LabelType,
     to_xml, AlternativeImageType
 )
 from ocrd import Processor
@@ -112,22 +110,10 @@ def process(self):
             file_id = make_file_id(input_file, self.output_file_grp)
 
             pcgts = page_from_file(self.workspace.download_file(input_file))
+            self.add_metadata(pcgts)
             page_id = pcgts.pcGtsId or input_file.pageId or input_file.ID # (PageType has no id)
             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()])]))
-            
             page_image, page_xywh, page_image_info = self.workspace.image_from_page(
                 page, page_id)
             if self.parameter['dpi'] > 0:
@@ -141,7 +127,7 @@ def process(self):
             else:
                 zoom = 1
 
-            regions = page.get_TextRegion()
+            regions = page.get_AllRegions(classes=['Text'])
             if not regions:
                 self.logger.warning('Page "%s" contains no text regions', page_id)
             for region in regions:

ocrd_cis/ocropy/recognize.py

@@ -17,8 +17,6 @@
 )
 from ocrd_modelfactory import page_from_file
 from ocrd_models.ocrd_page import (
-    MetadataItemType,
-    LabelsType, LabelType,
     to_xml, TextEquivType,
     CoordsType, GlyphType, WordType
 )
@@ -151,28 +149,16 @@ def process(self):
         for (n, input_file) in enumerate(self.input_files):
             self.logger.info("INPUT FILE %i / %s", n, input_file.pageId or input_file.ID)
             pcgts = page_from_file(self.workspace.download_file(input_file))
+            self.add_metadata(pcgts)
             page_id = pcgts.pcGtsId or input_file.pageId or input_file.ID # (PageType has no id)
             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()])]))
-
             page_image, page_coords, _ = self.workspace.image_from_page(
                 page, page_id)
 
             self.logger.info("Recognizing text in page '%s'", page_id)
             # region, line, word, or glyph level:
-            regions = page.get_TextRegion()
+            regions = page.get_AllRegions(classes=['Text'])
             if not regions:
                 self.logger.warning("Page '%s' contains no text regions", page_id)
             self.process_regions(regions, maxlevel, page_image, page_coords)

ocrd_cis/ocropy/resegment.py

@@ -9,8 +9,6 @@
 
 from ocrd_modelfactory import page_from_file
 from ocrd_models.ocrd_page import (
-    MetadataItemType,
-    LabelsType, LabelType,
     to_xml, AlternativeImageType
 )
 from ocrd import Processor
@@ -163,22 +161,10 @@ def process(self):
             file_id = make_file_id(input_file, self.output_file_grp)
 
             pcgts = page_from_file(self.workspace.download_file(input_file))
+            self.add_metadata(pcgts)
             page_id = pcgts.pcGtsId or input_file.pageId or input_file.ID # (PageType has no id)
             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()])]))
-            
             page_image, page_xywh, page_image_info = self.workspace.image_from_page(
                 page, page_id, feature_selector='binarized')
             if self.parameter['dpi'] > 0:
@@ -192,7 +178,7 @@ def process(self):
             else:
                 zoom = 1
 
-            regions = page.get_TextRegion()
+            regions = page.get_AllRegions(classes=['Text'])
             if not regions:
                 LOG.warning('Page "%s" contains no text regions', page_id)
             for region in regions:

ocrd_cis/ocropy/segment.py

@@ -11,8 +11,6 @@
 
 from ocrd_modelfactory import page_from_file
 from ocrd_models.ocrd_page import (
-    MetadataItemType,
-    LabelsType, LabelType,
     to_xml, CoordsType,
     TextLineType,
     TextRegionType,
@@ -216,22 +214,10 @@ def process(self):
             file_id = make_file_id(input_file, self.output_file_grp)
 
             pcgts = page_from_file(self.workspace.download_file(input_file))
+            self.add_metadata(pcgts)
             page_id = pcgts.pcGtsId or input_file.pageId or input_file.ID # (PageType has no id)
             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()])]))
-            
             # TODO: also allow grayscale_normalized (try/except?)
             page_image, page_coords, page_image_info = self.workspace.image_from_page(
                 page, page_id, feature_selector='binarized')