Created
May 31, 2018 15:34
-
-
Save pulsejet/8f37877556eddc7131bd84fbe40af631 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import nltk | |
import xml.etree.ElementTree as ET | |
import copy | |
import difflib | |
tree = ET.parse('xmlsdev.xml') | |
root = tree.getroot() | |
def xml_stringify(node): | |
return "".join(node.itertext()) | |
def custom_tokenize(sentence): | |
return(nltk.word_tokenize(xml_stringify(sentence).replace('-', ' - '))) | |
def remove_all_nodes(parent, childname): | |
for child in parent.findall(childname): | |
tail = child.tail | |
child.clear() | |
child.tail = tail | |
def diff_to_xml(diff): | |
return [diff_line_to_xml(x) for x in diff] | |
def diff_line_to_xml(line): | |
if line[0] == ' ': | |
return 'c' | |
if line[0] == '-': | |
return '<del>' + line[2:] + '</del>' | |
if line[0] == '+': | |
return '<ins>' + line[2:] + '</ins>' | |
with open('corrected', 'w', encoding='utf-8') as file: | |
i = 0 | |
for sentence in root.iter('sentence'): | |
sentence_c = copy.deepcopy(sentence) | |
remove_all_nodes(sentence, 'ins') | |
remove_all_nodes(sentence_c, 'del') | |
s1 = custom_tokenize(sentence) | |
s2 = custom_tokenize(sentence_c) | |
diff = difflib.ndiff(s1, s2) | |
file.write('\n'.join([x for x in diff_to_xml(diff) if x])) | |
file.write('\n') | |
if i%100 == 0: | |
print(i) | |
i += 1 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment