🐛 dinglehopper: Do not throw error if a region ID is not found

The ReadingOrder might contain regions of types other than text regions,
so not finding a TextRegion with the referenced ID is not an error.
Downgrade to a warning for now.

qurator/dinglehopper/ocr_files.py

@@ -1,5 +1,7 @@
 from __future__ import division, print_function
 
+from warnings import warn
+
 from lxml import etree as ET
 import sys
 
@@ -68,7 +70,7 @@ def page_text(tree):
                     if region is not None:
                         region_texts.append(region_text(region))
                     else:
-                        raise ValueError('Invalid region id "%s" in file' % region_id)
+                        warn('Not a TextRegion: "%s"' % region_id)
             else:
                 raise NotImplementedError
     else:

qurator/dinglehopper/tests/data/mixed-regions.page.xml

@@ -0,0 +1,290 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<pc:PcGts xmlns:pc="http://schema.primaresearch.org/PAGE/gts/pagecontent/2018-07-15">
+  <pc:Metadata>
+    <pc:Creator>OCR-D/core 1.0.0b19</pc:Creator>
+    <pc:Created>2019-09-26T11:59:19.519140</pc:Created>
+    <pc:LastChange>2019-09-26T11:59:19.519140</pc:LastChange>
+    <pc:MetadataItem type="processingStep" name="layout/segmentation/region" value="ocrd-tesserocr-segment-region">
+      <pc:Labels>
+        <pc:Label value="True" type="overwrite_regions"/>
+        <pc:Label value="8" type="padding"/>
+        <pc:Label value="False" type="crop_polygons"/>
+        <pc:Label value="True" type="find_tables"/>
+      </pc:Labels>
+    </pc:MetadataItem>
+    <pc:MetadataItem type="processingStep" name="layout/segmentation/line" value="ocrd-tesserocr-segment-line">
+      <pc:Labels>
+        <pc:Label value="True" type="overwrite_lines"/>
+      </pc:Labels>
+    </pc:MetadataItem>
+  </pc:Metadata>
+  <pc:Page imageFilename="../OCR-D-IMG-BIN/OCR-D-IMG-BIN_0001.png" imageWidth="1832" imageHeight="2408">
+    <pc:ReadingOrder>
+      <pc:OrderedGroup id="reading-order">
+        <pc:RegionRefIndexed index="0" regionRef="region0000"/>
+        <pc:RegionRefIndexed index="1" regionRef="region0001"/>
+        <pc:RegionRefIndexed index="2" regionRef="region0002"/>
+        <pc:RegionRefIndexed index="3" regionRef="region0003"/>
+      </pc:OrderedGroup>
+    </pc:ReadingOrder>
+    <pc:TextRegion id="region0001">
+      <pc:Coords points="184,196 1338,196 1338,1969 184,1969"/>
+      <pc:TextLine id="region0001_line0000">
+        <pc:Coords points="217,204 1324,204 1324,264 217,264"/>
+        <pc:TextEquiv>
+          <pc:Unicode>phariſei hypocritæ, qui comeditis domos uiduarã ſub</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0001">
+        <pc:Coords points="220,258 1325,258 1325,314 220,314"/>
+        <pc:TextEquiv>
+          <pc:Unicode>prætextu longarum precationum, propterea maiorẽ</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0002">
+        <pc:Coords points="218,305 1325,305 1325,359 218,359"/>
+        <pc:TextEquiv>
+          <pc:Unicode>accipieris condemnationem. Ideo enim ꝙ non oratis</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0003">
+        <pc:Coords points="217,354 1325,354 1325,413 217,413"/>
+        <pc:TextEquiv>
+          <pc:Unicode>ſecundum præſeriptum ſacræ ſcripturæ, nec ex ſpiritu</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0004">
+        <pc:Coords points="216,401 1322,401 1322,460 216,460"/>
+        <pc:TextEquiv>
+          <pc:Unicode>&amp; ueritate ſed iuxta ueſtram propriam conſtitutionẽ,</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0005">
+        <pc:Coords points="219,454 1324,454 1324,505 219,505"/>
+        <pc:TextEquiv>
+          <pc:Unicode>orationes ueſtræ nõ ſiunt Deo acceptæ, neq; ab eo ex⸗</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0006">
+        <pc:Coords points="219,501 1326,501 1326,563 219,563"/>
+        <pc:TextEquiv>
+          <pc:Unicode>audiunt᷑ Eſa, Cum multiplicaueritis orationes ueſtras</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0007">
+        <pc:Coords points="215,556 1325,556 1325,607 215,607"/>
+        <pc:TextEquiv>
+          <pc:Unicode>non exaudiam uos. Chriſtiani uero quia orant iuxta</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0008">
+        <pc:Coords points="218,605 1324,605 1324,665 218,665"/>
+        <pc:TextEquiv>
+          <pc:Unicode>tenorem ſcripturæ, &amp; ex ſpiritu &amp; ueritate, ideo eo⸗</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0009">
+        <pc:Coords points="217,651 1324,651 1324,707 217,707"/>
+        <pc:TextEquiv>
+          <pc:Unicode>rum orationes a Deo exaudiuntur, ſuntq; illi grat iſsi⸗</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0010">
+        <pc:Coords points="219,705 1322,705 1322,756 219,756"/>
+        <pc:TextEquiv>
+          <pc:Unicode>mæ, dicunt enim Pater noſter qui es iu cœlis &amp;c. Vos</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0011">
+        <pc:Coords points="218,756 1323,756 1323,806 218,806"/>
+        <pc:TextEquiv>
+          <pc:Unicode>autem hoc tenore orandi contempto, obmur muratis</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0012">
+        <pc:Coords points="218,803 1327,803 1327,854 218,854"/>
+        <pc:TextEquiv>
+          <pc:Unicode>ueſtras Horas canonicas, hoc eſt, diabolicas ab Anti⸗</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0013">
+        <pc:Coords points="218,852 1324,852 1324,904 218,904"/>
+        <pc:TextEquiv>
+          <pc:Unicode>chriſto inſtitutas. Paulus mauult quinq; uerba in Ec⸗</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0014">
+        <pc:Coords points="219,904 1323,904 1323,958 219,958"/>
+        <pc:TextEquiv>
+          <pc:Unicode>cle ſia loqui in ſenſu, qß decem milia uerborum in lin⸗</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0015">
+        <pc:Coords points="218,954 1326,954 1326,1010 218,1010"/>
+        <pc:TextEquiv>
+          <pc:Unicode>ua, Quibus uerbis adeo dãnat ueſtras prolixas ora⸗</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0016">
+        <pc:Coords points="192,1002 1324,1002 1324,1052 192,1052"/>
+        <pc:TextEquiv>
+          <pc:Unicode>tiones, ut ſi ſemiuncia ſanæ mentis uel mica ſidei eſfet</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0017">
+        <pc:Coords points="218,1055 965,1055 965,1101 218,1101"/>
+        <pc:TextEquiv>
+          <pc:Unicode>in uobis, eas ſine dubio omitteretis.</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0018">
+        <pc:Coords points="325,1103 1323,1103 1323,1160 325,1160"/>
+        <pc:TextEquiv>
+          <pc:Unicode>De inuocatione diuorum ne apiculus quidem ha</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0019">
+        <pc:Coords points="216,1156 1326,1156 1326,1212 216,1212"/>
+        <pc:TextEquiv>
+          <pc:Unicode>betur in ſacris literis, quare ter ſtulti eſtis quod inuo⸗</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0020">
+        <pc:Coords points="220,1210 1326,1210 1326,1262 220,1262"/>
+        <pc:TextEquiv>
+          <pc:Unicode>catis ſanctos, cum ex præce pto Dei ne mo inuocandus</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0021">
+        <pc:Coords points="218,1261 1326,1261 1326,1307 218,1307"/>
+        <pc:TextEquiv>
+          <pc:Unicode>ſit niſi ſolus Deus. Inuoca inquit me in die tribulatio⸗</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0022">
+        <pc:Coords points="222,1305 1324,1305 1324,1354 222,1354"/>
+        <pc:TextEquiv>
+          <pc:Unicode>nis. &amp; eruam te, &amp; honorificabis me. Et omnis qui⸗</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0023">
+        <pc:Coords points="221,1353 1324,1353 1324,1415 221,1415"/>
+        <pc:TextEquiv>
+          <pc:Unicode>cumq; inuocauerit nomen domini, ſaluus erit Sed</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0024">
+        <pc:Coords points="220,1404 1321,1404 1321,1465 220,1465"/>
+        <pc:TextEquiv>
+          <pc:Unicode>quomodo inuocabitis, in quem non credidiſtis? Quo</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0025">
+        <pc:Coords points="221,1456 1325,1456 1325,1508 221,1508"/>
+        <pc:TextEquiv>
+          <pc:Unicode>modo credetis ſine uerbo ? Inuocationẽ ergo in ſcrip⸗</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0026">
+        <pc:Coords points="222,1509 1323,1509 1323,1559 222,1559"/>
+        <pc:TextEquiv>
+          <pc:Unicode>turis non legitis cõmemorationem uero ſæpe, non ut</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0027">
+        <pc:Coords points="222,1555 1330,1555 1330,1612 222,1612"/>
+        <pc:TextEquiv>
+          <pc:Unicode>intercedant pro uobis ſancti, ſed nt meminerit Deus</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0028">
+        <pc:Coords points="219,1604 1325,1604 1325,1664 219,1664"/>
+        <pc:TextEquiv>
+          <pc:Unicode>Teſtamenti cum patribus ſanctis pacti, ut ſimiliter uo⸗</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0029">
+        <pc:Coords points="218,1653 1323,1653 1323,1719 218,1719"/>
+        <pc:TextEquiv>
+          <pc:Unicode>biſcum agat per miſericordiam, quemadmodum cum</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0030">
+        <pc:Coords points="219,1704 1321,1704 1321,1769 219,1769"/>
+        <pc:TextEquiv>
+          <pc:Unicode>ilis egit. Atq; hoc non eſt inuocare ſanctos. ſed Deum</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0031">
+        <pc:Coords points="222,1758 1322,1758 1322,1817 222,1817"/>
+        <pc:TextEquiv>
+          <pc:Unicode>ſuæ miſericordiæ &amp; promiſsionis admonere Sic pſal</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0032">
+        <pc:Coords points="224,1809 1324,1809 1324,1866 224,1866"/>
+        <pc:TextEquiv>
+          <pc:Unicode>mographus dicit, Qui paſcis Iſrael attende, qui de⸗</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0033">
+        <pc:Coords points="222,1858 1320,1858 1320,1913 222,1913"/>
+        <pc:TextEquiv>
+          <pc:Unicode>ducis uelut ouem Iacob Sic &amp; Moſes orat, Memento</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextLine id="region0001_line0034">
+        <pc:Coords points="345,1909 1320,1909 1320,1963 345,1963"/>
+        <pc:TextEquiv>
+          <pc:Unicode>B 3 domi⸗</pc:Unicode>
+        </pc:TextEquiv>
+      </pc:TextLine>
+      <pc:TextEquiv>
+        <pc:Unicode>phariſei hypocritæ, qui comeditis domos uiduarã ſub
+prætextu longarum precationum, propterea maiorẽ
+accipieris condemnationem. Ideo enim ꝙ non oratis
+ſecundum præſeriptum ſacræ ſcripturæ, nec ex ſpiritu
+&amp; ueritate ſed iuxta ueſtram propriam conſtitutionẽ,
+orationes ueſtræ nõ ſiunt Deo acceptæ, neq; ab eo ex⸗
+audiunt᷑ Eſa, Cum multiplicaueritis orationes ueſtras
+non exaudiam uos. Chriſtiani uero quia orant iuxta
+tenorem ſcripturæ, &amp; ex ſpiritu &amp; ueritate, ideo eo⸗
+rum orationes a Deo exaudiuntur, ſuntq; illi grat iſsi⸗
+mæ, dicunt enim Pater noſter qui es iu cœlis &amp;c. Vos
+autem hoc tenore orandi contempto, obmur muratis
+ueſtras Horas canonicas, hoc eſt, diabolicas ab Anti⸗
+chriſto inſtitutas. Paulus mauult quinq; uerba in Ec⸗
+cle ſia loqui in ſenſu, qß decem milia uerborum in lin⸗
+ua, Quibus uerbis adeo dãnat ueſtras prolixas ora⸗
+tiones, ut ſi ſemiuncia ſanæ mentis uel mica ſidei eſfet
+in uobis, eas ſine dubio omitteretis.
+De inuocatione diuorum ne apiculus quidem ha
+betur in ſacris literis, quare ter ſtulti eſtis quod inuo⸗
+catis ſanctos, cum ex præce pto Dei ne mo inuocandus
+ſit niſi ſolus Deus. Inuoca inquit me in die tribulatio⸗
+nis. &amp; eruam te, &amp; honorificabis me. Et omnis qui⸗
+cumq; inuocauerit nomen domini, ſaluus erit Sed
+quomodo inuocabitis, in quem non credidiſtis? Quo
+modo credetis ſine uerbo ? Inuocationẽ ergo in ſcrip⸗
+turis non legitis cõmemorationem uero ſæpe, non ut
+intercedant pro uobis ſancti, ſed nt meminerit Deus
+Teſtamenti cum patribus ſanctis pacti, ut ſimiliter uo⸗
+biſcum agat per miſericordiam, quemadmodum cum
+ilis egit. Atq; hoc non eſt inuocare ſanctos. ſed Deum
+ſuæ miſericordiæ &amp; promiſsionis admonere Sic pſal
+mographus dicit, Qui paſcis Iſrael attende, qui de⸗
+ducis uelut ouem Iacob Sic &amp; Moſes orat, Memento
+B 3 domi⸗</pc:Unicode>
+      </pc:TextEquiv>
+    </pc:TextRegion>
+    <pc:ImageRegion id="region0000">
+      <pc:Coords points="5,21 1790,21 1790,302 5,302"/>
+    </pc:ImageRegion>
+    <pc:ImageRegion id="region0002">
+      <pc:Coords points="0,1962 1813,1962 1813,2361 0,2361"/>
+    </pc:ImageRegion>
+    <pc:ImageRegion id="region0003">
+      <pc:Coords points="1316,166 1790,166 1790,238 1316,238"/>
+    </pc:ImageRegion>
+  </pc:Page>
+</pc:PcGts>

qurator/dinglehopper/tests/test_ocr_files.py

@@ -4,6 +4,8 @@ import re
 import lxml.etree as ET
 import textwrap
 
+import pytest
+
 from .. import alto_namespace, alto_text, page_namespace, page_text, text
 
 data_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'data')
@@ -93,6 +95,15 @@ def test_page_order():
     assert re.search(r'Herr Konfrater.*75.*Etwas f.r Wittwen.*Ein gewi.er Lord.*76\. Die', result, re.DOTALL)
 
 
+def test_page_mixed_regions():
+    # This file contains ImageRegions and TextRegions in the ReadingOrder
+    tree = ET.parse(os.path.join(data_dir, 'mixed-regions.page.xml'))
+    with pytest.warns(UserWarning, match=r'Not a TextRegion'):
+        result = page_text(tree)
+
+    assert 'non exaudiam uos. Chriſtiani uero quia orant iuxta' in result
+
+
 def test_text():
     assert "being erected at the Broadway stock" in text(os.path.join(data_dir, 'test.alto1.xml'))
     assert "wieder ein. — Er langte den Zettel aus dem" in text(os.path.join(data_dir, 'test.page2018.xml'))