Notes

from bs4 import BeautifulSoup as BS
from bs4.element import NavigableString
import copy
import re
import numpy as np
import pandas as pd
from lxml import etree


filename = "123.xlf"
excel_translated = 'translated.xlsx'

with open(filename, 'r', encoding='UTF-8') as f:
src = f.read()

df = pd.read_excel(excel_translated) # Translated Excel
col1 = df['Text'].astype(str)
col2 = df['Text-Copy'].astype(str)
# print(col1)
# print(col2)

# Create dictionary-----------
translation_dict = dict(zip(col1, col2))
print(str(translation_dict))

src_start = "<source"
src_end = "</source>"
start_ind = [i.start() for i in re.finditer(src_start, src)]
end_ind = [i.start() for i in re.finditer(src_end, src)]

offset = 0

for i in range(len(start_ind)):
sub_str = src[start_ind[i]+offset:end_ind[i]+len(src_end)+offset]
offset = offset + len(sub_str)
sub_str = sub_str.replace('<source', '<target')
sub_str = sub_str.replace('</source>', '</target>')
# Append the <target> block
src = src[:start_ind[i]+offset] + sub_str + src[start_ind[i]+offset:]
# src_blocks.append(sub_str)
# print(src)
# print("Block #%s::n" %(i+1), src_blocks[i])
# print(src)

tag_list = ['g']
soup = BS(src, 'lxml')
tags = {tag.name for tag in soup.find_all()}
for tag in tags:
if tag == 'g':
for ele in soup.find_all(tag):
# print(ele.text)
g_text = ele.text

new_txt = translation_dict[g_text]
# start_ind = [i.start() for i in re.finditer(g_text, src)]

# tag.string = new_txt


with open('duplicate.xlf', 'w', encoding='UTF-8') as f:
f.write(src)

tree = etree.parse('duplicate.xlf')
root = tree.getroot()


for element in root:
pass # not important
# now the children
for all_tags in element.findall('.//'):
if 'target' in all_tags.tag:
if all_tags.text is not None:
tgt_text = all_tags.text
new_text = translation_dict[tgt_text]
all_tags.text = new_text
# print(src)
tree.write('duplicate_v1.xlf')
# with open('output.xlf', 'w', encoding='UTF-8') as f:
# f.write(src)