Adapt to 1.0.0b6, write out result

Makefile

@@ -11,6 +11,7 @@ help:
 	@echo "    install    pip install -e ."
 	@echo "    uninstall  pip uninstall $(PKG_NAME)"
 	@echo "    assets     Fetch test assets"
+	@echo "    test       Run tests"
 	@echo ""
 	@echo "  Variables"
 	@echo ""

ocrd_typegroups_classifier/processor.py

@@ -3,16 +3,15 @@
 """
 
 from ocrd import Processor
-from ocrd.model.ocrd_page import (
-    from_file,
+from ocrd_utils import getLogger, concat_padded, MIMETYPE_PAGE
+from ocrd_models.ocrd_page import (
     to_xml
 )
+from ocrd_modelfactory import page_from_file
 
 from .typegroups_classifier import TypegroupsClassifier
 from .constants import OCRD_TOOL
 
-from ocrd.utils import getLogger
-
 
 class TypegroupsClassifierProcessor(Processor):
 
@@ -26,20 +25,21 @@ def process(self):
         network_file = self.parameter['network']
         stride = self.parameter['stride']
         classifier = TypegroupsClassifier.load(network_file)
-
-        ignore_type = ('Adornment', 'Book covers and other irrelevant data', 'Empty Pages', 'Woodcuts - Engravings')
-
-        self.log.debug('Processing: ', self.input_files)
+
+        ignore_type = ('Adornment', 'Book covers and other irrelevant data',
+                       'Empty Pages', 'Woodcuts - Engravings')
+
+        self.log.debug('Processing: %s', self.input_files)
         for (_, input_file) in enumerate(self.input_files):
-            pcgts = from_file(self.workspace.download_file(input_file))
+            pcgts = page_from_file(self.workspace.download_file(input_file))
             image_url = pcgts.get_Page().imageFilename
             pil_image = self.workspace.resolve_image_as_pil(image_url)
             result = classifier.run(pil_image, stride)
             score_sum = 0
             for typegroup in classifier.classMap.cl2id:
                 if not typegroup in ignore_type:
                     score_sum += max(0, result[typegroup])
-            
+
             script_highscore = 0
             noise_highscore = 0
             result_map = {}
@@ -52,13 +52,23 @@ def process(self):
                     script_highscore = max(script_highscore, score)
                     normalised_score = max(0, score / score_sum)
                     result_map[normalised_score] = typegroup
-            if noise_highscore>script_highscore:
+            if noise_highscore > script_highscore:
                 pcgts.get_Page().set_primaryScript(None)
-                self.log.debug('Detected only noise (such as empty page or book cover)')
+                self.log.debug(
+                    'Detected only noise (such as empty page or book cover). noise_highscore=%s > script_highscore=%s',
+                    noise_highscore, script_highscore)
             else:
                 for k in sorted(result_map, reverse=True):
-                    if output!='':
+                    if output != '':
                         output = '%s, ' % output
                     output = '%s%s:%d' % (output, result_map[k], round(100*k))
-                pcgts.get_Page().set_primaryScript(output)
                 self.log.debug('Detected %s' % output)
+                pcgts.get_Page().set_primaryScript(output)
+                ID = concat_padded(self.output_file_grp, input_file.ID)
+                self.workspace.add_file(
+                    ID=ID,
+                    file_grp=self.output_file_grp,
+                    mimetype=MIMETYPE_PAGE,
+                    local_filename="%s/%s" % (self.output_file_grp, ID),
+                    content=to_xml(pcgts)
+                )

requirements.txt

@@ -1,7 +1 @@
-click
-ocrd >= 0.11.0
-pandas
-Pillow >= 5.3.0
-scikit-image
-torch
-torchvision
+.

setup.py

@@ -11,6 +11,7 @@
     version='0.0.1',
     description='Typegroups classifier for OCR',
     long_description=README,
+    long_description_content_type='text/markdown',
     author='Matthias Seuret, Konstantin Baierer',
     author_email='seuretm@users.noreply.github.com',
     url='https://github.com/seuretm/ocrd_typegroups_classifier',
@@ -19,7 +20,7 @@
     include_package_data=True,
     install_requires=[
         'click',
-        'ocrd >= 0.11.0',
+        'ocrd >= 1.0.0b6',
         'pandas',
         'Pillow >= 5.3.0',
         'scikit-image',

tests/test.sh

@@ -8,7 +8,7 @@ net="${SCRIPTDIR}/../ocrd_typegroups_classifier/models/classifier.tgc"
 cd "$SCRIPTDIR/assets/pembroke_werke_1766/data"
 ocrd-typegroups-classifier \
     -l DEBUG \
-    -g FILE_0010_DEFAULT \
+    -g PHYS_0011 \
     -m mets.xml \
     -I DEFAULT \
     -O "OCR-D-FONTIDENT" \