"Skirzěňž" et al.

dan-zeman · dan-zeman · commit f747fa0b8180 · 2024-10-14T09:45:07.000+02:00
diff --git a/udapi/block/ud/cs/addmwt.py b/udapi/block/ud/cs/addmwt.py
@@ -76,6 +76,17 @@
         'main': 1,
         'shape': 'subtree',
     }
+for prep in 'skirzě skrzě skrze'.split():
+    MWTS[prep + 'ň'] = {
+        'form': prep + ' něj',
+        'lemma': 'skrz on',
+        'upos': 'ADP PRON',
+        'xpos': 'RV--4---------- PEZS4--3-------',
+        'feats': 'AdpType=Voc|Case=Acc Case=Acc|Gender=Masc,Neut|Number=Sing|Person=3|PrepCase=Pre|PronType=Prs',
+        'deprel': 'case *',
+        'main': 1,
+        'shape': 'subtree',
+    }
 
 # Define static rules for 'naňž', 'oňž', 'proňž', 'zaňž'.
 # Add them to the already existing dictionary MWTS.
@@ -91,6 +102,18 @@
         'main': 1,
         'shape': 'subtree',
     }
+# Additional contractions in Old Czech with vocalization.
+for prep in 'skirzě skrzě skrze'.split():
+    MWTS[prep + 'ňž'] = {
+        'form': prep + ' nějž',
+        'lemma': 'skrz jenž',
+        'upos': 'ADP PRON',
+        'xpos': 'RV--4---------- P4ZS4---------2',
+        'feats': 'AdpType=Voc|Case=Acc Case=Acc|Gender=Masc,Neut|Number=Sing|PrepCase=Pre|PronType=Rel',
+        'deprel': 'case *',
+        'main': 1,
+        'shape': 'subtree',
+    }
 
 class AddMwt(udapi.block.ud.addmwt.AddMwt):
     """Detect and mark MWTs (split them into words and add the words to the tree)."""
