lkrsnik/stress_asignment
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Added some fixes in converting sloleks to the one with stressed words

Browse Source
This commit is contained in:
lkrsnik 2018-08-22 08:01:06 +02:00
parent 902de059be
commit 36c8880bfe
2 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
sloleks_accentuation2.py
View File

@ -46,7 +46,7 @@ print('Commencing accentuator!')
rate = 100000
start_timer = time.time()
with open("data/new_sloleks/new_sloleks.tab", "a") as myfile:
with open("data/new_sloleks/new_sloleks2.tab", "a") as myfile:
for index in range(300000, len(new_content), rate):
if index+rate >= len(new_content):
words = [[el[0], '', el[2], el[0]] for el in new_content][index:len(new_content)]

7
sloleks_accentuation2_tab2xml.py
View File

@ -52,14 +52,14 @@ word_index = 0
# done_lexical_entries = 33522
data = Data('s', shuffle_all_inputs=False)
accentuated_content = data._read_content('data/new_sloleks/new_sloleks.tab')
accentuated_content = data._read_content('data/new_sloleks/final_sloleks2.tab')
start_timer = time.time()
print('Copy initialization complete')
with open("data/new_sloleks/final_sloleks.xml", "ab") as myfile:
with open("data/new_sloleks/final_sloleks2.xml", "ab") as myfile:
# myfile2 = open('data/new_sloleks/p' + str(iter_index) + '.xml', 'ab')
for event, element in etree.iterparse('data/new_sloleks/final_sloleks_read.xml', tag="LexicalEntry", encoding="UTF-8", remove_blank_text=True):
for event, element in etree.iterparse('data/Sloleks_v1.2.xml', tag="LexicalEntry", encoding="UTF-8", remove_blank_text=True):
# for event, element in etree.iterparse('data/Sloleks_v1.2.xml', tag="LexicalEntry", encoding="UTF-8", remove_blank_text=True):
# if word_glob_num >= word_limit:
# myfile2.close()
@ -135,6 +135,7 @@ with open("data/new_sloleks/final_sloleks.xml", "ab") as myfile:
new_element = etree.Element('feat')
new_element.attrib['att'] = 'SAMPA'
print(accentuated_word)
new_element.attrib['val'] = convert_to_SAMPA(accentuated_word)
wf.append(new_element)