test for #686

OCR-D · Apr 26, 2021 · 076ef5c · 076ef5c
1 parent 0a34771
commit 076ef5c
Show file tree

Hide file tree

Showing 10 changed files with 82 additions and 0 deletions.
diff --git a/tests/data/sample-features/foo0.png b/tests/data/sample-features/foo0.png
diff --git a/tests/data/sample-features/foo1.png b/tests/data/sample-features/foo1.png
diff --git a/tests/data/sample-features/foo2.png b/tests/data/sample-features/foo2.png
diff --git a/tests/data/sample-features/foo3.png b/tests/data/sample-features/foo3.png
diff --git a/tests/data/sample-features/foo4.png b/tests/data/sample-features/foo4.png
diff --git a/tests/data/sample-features/foo5.png b/tests/data/sample-features/foo5.png
diff --git a/tests/data/sample-features/foo6.png b/tests/data/sample-features/foo6.png
diff --git a/tests/data/sample-features/image_features.page.xml b/tests/data/sample-features/image_features.page.xml
@@ -0,0 +1,16 @@
+<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<PcGts xmlns="http://schema.primaresearch.org/PAGE/gts/pagecontent/2019-07-15" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://schema.primaresearch.org/PAGE/gts/pagecontent/2013-07-15 http://schema.primaresearch.org/PAGE/gts/pagecontent/2013-07-15/pagecontent.xsd" pcGtsId="PAGE_0017_PAGE">
+    <Metadata>
+        <Creator>OCR-D</Creator>
+        <Created>2016-09-20T11:09:27.041+02:00</Created>
+        <LastChange>2018-04-25T17:44:49.605+01:00</LastChange>
+    </Metadata>
+    <Page imageFilename="foo0.png" imageWidth="1457" imageHeight="2083" type="content">
+        <AlternativeImage filename="foo1.png" comments="binarized"/>
+        <AlternativeImage filename="foo2.png" comments="dewarped,cropped"/>
+        <AlternativeImage filename="foo3.png" comments="cropped,binarized"/>
+        <AlternativeImage filename="foo4.png" comments="cropped,dewarped,binarized,despeckled,deskewed"/>
+        <AlternativeImage filename="foo5.png" comments="cropped,dewarped,despeckled"/>
+        <Border><Coords points="101,232 932,232 932,1794 101,1794"/></Border>
+    </Page>
+</PcGts>
diff --git a/tests/data/sample-features/mets.xml b/tests/data/sample-features/mets.xml
@@ -0,0 +1,56 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<mets:mets xmlns:mets="http://www.loc.gov/METS/" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="info:lc/xmlns/premis-v2 http://www.loc.gov/standards/premis/v2/premis-v2-0.xsd http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-6.xsd http://www.loc.gov/METS/ http://www.loc.gov/standards/mets/version17/mets.v1-7.xsd http://www.loc.gov/mix/v10 http://www.loc.gov/standards/mix/mix10/mix10.xsd">
+  <mets:metsHdr CREATEDATE="2021-04-26T13:16:13.397420">
+    <mets:agent TYPE="OTHER" OTHERTYPE="SOFTWARE" ROLE="CREATOR">
+      <mets:name>ocrd/core v2.23.3</mets:name>
+    </mets:agent>
+  </mets:metsHdr>
+  <mets:dmdSec ID="DMDLOG_0001">
+    <mets:mdWrap MDTYPE="MODS">
+      <mets:xmlData>
+        <mods:mods xmlns:mods="http://www.loc.gov/mods/v3">
+                </mods:mods>
+      </mets:xmlData>
+    </mets:mdWrap>
+  </mets:dmdSec>
+  <mets:amdSec ID="AMD">
+    </mets:amdSec>
+  <mets:fileSec>
+    <mets:fileGrp USE="FOO">
+      <mets:file MIMETYPE="application/vnd.prima.page+xml" ID="foo0">
+        <mets:FLocat LOCTYPE="OTHER" OTHERLOCTYPE="FILE" xlink:href="image_features.page.xml"/>
+      </mets:file>
+      <mets:file MIMETYPE="image/png" ID="foo1">
+        <mets:FLocat LOCTYPE="OTHER" OTHERLOCTYPE="FILE" xlink:href="foo1"/>
+      </mets:file>
+      <mets:file MIMETYPE="image/png" ID="foo2">
+        <mets:FLocat LOCTYPE="OTHER" OTHERLOCTYPE="FILE" xlink:href="foo2"/>
+      </mets:file>
+      <mets:file MIMETYPE="image/png" ID="foo3">
+        <mets:FLocat LOCTYPE="OTHER" OTHERLOCTYPE="FILE" xlink:href="foo3"/>
+      </mets:file>
+      <mets:file MIMETYPE="image/png" ID="foo4">
+        <mets:FLocat LOCTYPE="OTHER" OTHERLOCTYPE="FILE" xlink:href="foo4"/>
+      </mets:file>
+      <mets:file MIMETYPE="image/png" ID="foo5">
+        <mets:FLocat LOCTYPE="OTHER" OTHERLOCTYPE="FILE" xlink:href="foo5"/>
+      </mets:file>
+      <mets:file MIMETYPE="image/png" ID="foo6">
+        <mets:FLocat LOCTYPE="OTHER" OTHERLOCTYPE="FILE" xlink:href="foo6"/>
+      </mets:file>
+    </mets:fileGrp>
+  </mets:fileSec>
+  <mets:structMap TYPE="PHYSICAL">
+    <mets:div TYPE="physSequence">
+      <mets:div TYPE="page" ID="page1">
+        <mets:fptr FILEID="foo0"/>
+        <mets:fptr FILEID="foo1"/>
+        <mets:fptr FILEID="foo2"/>
+        <mets:fptr FILEID="foo3"/>
+        <mets:fptr FILEID="foo4"/>
+        <mets:fptr FILEID="foo5"/>
+        <mets:fptr FILEID="foo6"/>
+      </mets:div>
+    </mets:div>
+  </mets:structMap>
+</mets:mets>
diff --git a/tests/test_workspace.py b/tests/test_workspace.py
@@ -297,6 +297,16 @@ def test_image_from_page_basic(self):
             img, info, exif = ws.image_from_page(pcgts.get_Page(), page_id='PHYS_0017')
             self.assertEquals(info['features'], 'binarized,clipped')
 
+    def test_image_feature_selectoro(self):
+        with pushd_popd('tests/data/sample-features'):
+            ws = self.resolver.workspace_from_url('mets.xml')
+            with open('image_features.page.xml', 'r') as f:
+                pcgts = parseString(f.read().encode('utf8'), silence=True)
+            img, info, exif = ws.image_from_page(pcgts.get_Page(), page_id='page1', feature_selector='dewarped')
+            self.assertEquals(info['features'], 'cropped,dewarped,binarized,despeckled,deskewed')
+            img, info, exif = ws.image_from_page(pcgts.get_Page(), page_id='page1', feature_selector='dewarped', feature_filter='binarized')
+            self.assertEquals(info['features'], 'cropped,dewarped,despeckled')
+
     def test_downsample_16bit_image(self):
         with pushd_popd(tempdir=True) as tempdir:
             with gzip_open(join(dirname(__file__), 'data/OCR-D-IMG_APBB_Mitteilungen_62.0002.tif.gz'), 'rb') as gzip_in: