def unknown_entry_partially_encode(entry):
old_morph_part = copy(entry.encoded_parts['morph_part'])
entry.encoded_parts['morph_part'] = []
counter = 0
while old_morph_part:
content_node = [old_morph_part[0]]
node_content = SafeString(old_morph_part[0].text)
if counter == 0:
content_node = unknown_initial_xml(content_node[0].text)
elif node_content.strip().startswith(
'(') and node_content.strip().endswith(')'):
content_node = [nf.create_extra_morph(node_content)]
elif node_content.strip() in (punctuation + '–'):
content_node = [nf.create_pc_node(node_content)]
elif old_morph_part[0].get('rend') == "italic":
if node_content.strip() in ('m', 'f', 'n'):
content_node = [nf.create_gram_grp(node_content)]
elif len(entry.encoded_parts['morph_part']) == 1 and len(old_morph_part) >= 2 and old_morph_part[1].get('rend' ) == 'bold' and \
node_content.strip() == 'и' and entry.encoded_parts['morph_part'][0].tag == nf.get_ns('form'):
content_node = []
entry.encoded_parts['morph_part'][0].append(old_morph_part[0])
entry.encoded_parts['morph_part'][0].append(
nf.create_orth_node(SafeString(old_morph_part[1].text)))
old_morph_part.pop(0)
else:
content_node = nf.create_usg_node(node_content)
elif node_content.strip() in ('1', '2', '3', '4') and (
len(old_morph_part) == 1
or old_morph_part[1].text.strip() != '.'):
content_node = [nf.create_gram_grp(node_content, 'iType')]
[entry.encoded_parts['morph_part'].append(x) for x in content_node]
old_morph_part.pop(0)
counter += 1
def noun_xml(content0, content1):
result = []
content0_split = content0.rsplit(', ', 1)
form_lemma = nf.create_form_lemma_node(content0_split[0])
result.append(form_lemma)
if content0_split[1]:
pc = nf.create_pc_node(', ')
form_inflected = nf.create_form_inflected_node(content0_split[1])
result.append(pc)
result.append(form_inflected)
gram_grp = nf.create_gram_grp(content1)
result.append(gram_grp)
return result
def verb_xml(entry_type, content0, content1):
result = []
content0_split = content0.split(', ')
form_lemma = nf.create_form_lemma_node(content0_split[0])
result.append(form_lemma)
if len(content0_split) > 1:
for word in content0_split[1:]:
pc = nf.create_pc_node(', ')
form_inflected = nf.create_form_inflected_node(word)
result.append(pc)
result.append(form_inflected)
if entry_type != 'special_verb':
gram_grp = nf.create_gram_grp(content1, "iType")
result.append(gram_grp)
return result
def adj_1_2_decl_xml(content0, content1):
form_lemma = nf.create_form_lemma_node(content0)
gram_grp = nf.create_gram_grp(content1, "????")
return [form_lemma, gram_grp]
def adv_conjunct_xml(content0, content1):
form_lemma = nf.create_form_lemma_node(content0)
gram_grp = nf.create_gram_grp(content1, "????")
return [form_lemma, gram_grp]