Added modifications to validate xsd

scripts/create_xml.py

@@ -382,7 +382,7 @@ def create_sentence_output(sentence, headword_id, corpus, sent_id):
     headword_id = str(headword_id)
     parent_node = etree.Element('corpusExample')
     parent_node.set('corpusName', corpus)
-    parent_node.set('id', sent_id)
+    parent_node.set('exampleId', sent_id)
     # parent_node.text = 'AAA'
     # parent_node.prefix = 'BBB'
     # parent_node.tail = 'CCC'
@@ -911,10 +911,10 @@ def write_xml(headword_category, collection_ssj, collection_gigafida, RF, mongo,
             #     .filter(Feature.name == 'aspect').all()
         else:
             frequency = None
-            lexeme_id = 0
-            lexical_unit_id = 0
-            lexical_unit_lexeme_id = 0
-            lexical_unit_type_name = ''
+            lexeme_id = None
+            lexical_unit_id = None
+            lexical_unit_lexeme_id = None
+            lexical_unit_type_name = None
             sense_ids = []
             features = []
 
@@ -928,11 +928,14 @@ def write_xml(headword_category, collection_ssj, collection_gigafida, RF, mongo,
         lemma.text = headword_text
 
         lexical_unit = lxml.SubElement(head, 'lexicalUnit')
-        lexical_unit.set('id', str(lexical_unit_id))
-        lexical_unit_type_name = 'single' if lexical_unit_type_name == 'single_lexeme_unit' else lexical_unit_type_name
-        lexical_unit.set('type', lexical_unit_type_name)
+        if lexical_unit_id is not None:
+            lexical_unit.set('id', str(lexical_unit_id))
+        if lexical_unit_type_name is not None:
+            lexical_unit_type_name = 'single' if lexical_unit_type_name == 'single_lexeme_unit' else lexical_unit_type_name
+            lexical_unit.set('type', lexical_unit_type_name)
         lexeme = lxml.SubElement(lexical_unit, 'lexeme')
-        lexeme.set('lexical_unit_lexeme_id', str(lexical_unit_lexeme_id))
+        if lexical_unit_lexeme_id is not None:
+            lexeme.set('lexical_unit_lexeme_id', str(lexical_unit_lexeme_id))
         lexeme.text = headword_text
 
         grammar = lxml.SubElement(head, 'grammar')
@@ -947,8 +950,6 @@ def write_xml(headword_category, collection_ssj, collection_gigafida, RF, mongo,
             ssj_frequency = ssj_frequency_dict[(headword_text, features[0].value)] if (headword_text, features[0].value) in ssj_frequency_dict else None
             if args.language == 'sl':
                 grammarFeature.set('name', 'vid')
-                if len(features) > 1:
-                    print(features)
                 grammarFeature.text = ASPECT_MAP[features[0].value]
             else:
                 grammarFeature.set('name', 'aspect')