set @type as well as TAGREFS from PAGE @type, #4

OCR-D · Apr 13, 2021 · aea4424 · aea4424
1 parent 5cac144
commit aea4424
Show file tree

Hide file tree

Showing 3 changed files with 5 additions and 2 deletions.
diff --git a/README.md b/README.md
@@ -12,10 +12,10 @@
 * [x] TextStyle
 * [x] ParagraphStyle
 * [x] table regions
-* [ ] recursive regions
+* [ ] recursive regions, #
 * [ ] rotation
 * [x] reading order
-* [x] input PAGE-XML not having words
+* [x] input PAGE-XML not having words #5
 * [x] multiple pc:TextEquivs
 * [x] language
 * [X] ~~script~~ no equivalent in ALTO :(

diff --git a/ocrd_page_to_alto/styles.py b/ocrd_page_to_alto/styles.py
@@ -122,5 +122,6 @@ def __init__(self):
     def set_alto_tag_from_type(self, reg_alto, reg_page):
         typ = reg_page.get_type() if hasattr(reg_page, 'get_type') else None
         if typ:
+            reg_alto.set('TYPE', typ)
             reg_alto.set('TAGREFS', self.get_id(label=typ))
 
diff --git a/tests/test_convert.py b/tests/test_convert.py
@@ -58,6 +58,8 @@ def test_layouttag():
     c = OcrdPageAltoConverter(page_filename='tests/data/layouttag.page.xml').convert()
     tree = ET.fromstring(str(c).encode('utf-8'))
     assert [x.get('LABEL') for x in tree.xpath('//alto:Tags/alto:LayoutTag', namespaces=NAMESPACES)] == ['paragraph']
+    assert len(tree.xpath('//*[@TYPE="paragraph"]')) == 1
+    assert len(tree.xpath('//*[@TYPE="catch-word"]')) == 0 # @TYPE only allowed for BlockType
 
 def test_pararaphstyle():
     c = OcrdPageAltoConverter(page_filename='tests/data/align.page.xml').convert()