lkrsnik/cjvt-valency
1
0
Fork 0
forked from kristjan/cjvt-valency
Code Issues Pull Requests Releases Wiki Activity

Added modifications to validate xsd

Browse Source
This commit is contained in:
Luka 2020-12-09 07:47:55 +01:00
parent 69c3521e4b
commit ec083a8d63
1 changed files with 12 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
scripts/create_xml.py
View File

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