Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fix on translating special characters #12

Open
wants to merge 5 commits into
base: main
Choose a base branch
from
Open

Fix on translating special characters #12

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
49bebb9
Fix on translating special characters
jonata Jan 29, 2021
c9ab605
Small fix for special characters
jonata Jan 29, 2021
38def24
Fix file name for setup.py
jonata Jan 29, 2021
fb3ce1b
This allows str to have newline char and other ascii
jonata Jan 29, 2021
1bb8ef8
Maybe a better approach to use a parser
jonata Jan 29, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
0 README.rst → README.md
View file
Open in desktop
File renamed without changes.
50 changes: 40 additions & 10 deletions pygoogletranslation/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,10 +31,10 @@ def format_querystring(token, text, src='auto', dest='en'):
def format_param(rpcids):
params = {
'rpcids': rpcids,
'bl': 'boq_translate-webserver_20201207.13_p0',
'soc-app': 1,
'soc-platform': 1,
'soc-device': 1,
'bl': 'boq_translate-webserver_20201207.13_p0',
'soc-app': 1,
'soc-platform': 1,
'soc-device': 1,
'rt': 'c'
}
return params
Expand All @@ -59,11 +59,34 @@ def format_response(a):
flag = not flag
_b = 'pygoogletranslation'
if flag:
# Parsing to cleanup "unescaped escaped" characters
if '\\' in _b:
_bp = ''
p = 0
while p < len(_b):
if _b[p:p+2] == '\\\\':
_bp += '\\'
p += 2
elif _b[p:p+1] == '\\':
if _b[p:p+2] == '\\u':
_bp += bytes(_b[p:p+6], 'ascii').decode('unicode-escape')
p += 6
elif _b[p:p+2] == '\\n':
_bp += '\n'
p += 2
else:
p += 1
else:
_bp += _b[p:p+1]
p += 1
_b = _bp

li_filter.append(_b)
fi_data = str(''.join(li_filter)).replace('"[', '[').replace(']"', ']').replace('\\n', '').replace('\\','')
li_data = json.loads(fi_data.split('pygoogletranslation')[1].replace('"[', '[').replace(']"', ']'))

fi_data = str(''.join(li_filter)).replace('","[', '",[', 1).replace('\n",null', '\n,null')
li_data = json.loads(fi_data.split('pygoogletranslation')[1], strict=False)
return li_data

def tokenize_sentence(text):
text_len = 0
token_text = ''
Expand All @@ -90,14 +113,20 @@ def format_translation(translated):
pron = ''
for _translated in translated:
try:
text += _translated[0][2][1][0][0][5][0][0]
if len(_translated[0][2][1][0][0][5]) > 1:
for phrase in _translated[0][2][1][0][0][5]:
text += ' ' + phrase[0]
else:
text += _translated[0][2][1][0][0][5][0][0]
except:
text += fix_trans_error(_translated)
try:
pron += unidecode.unidecode(_translated[0][2][1][0][0][1])
except:
pron += ''

text = text.strip()

for _translated in translated:
try:
_translated[0][2][1][0][0][5][0][0] = text
Expand All @@ -118,7 +147,9 @@ def fix_trans_error(translated):
if len(translated[0][2][1]) > 0:
if len(translated[0][2][1][0]) > 0:
if len(translated[0][2][1][0][0]) > 5:
if len(translated[0][2][1][0][0][5]) > 0:
if translated[0][2][1][0][0][5] is None:
text = translated[0][2][1][0][0][0]
elif len(translated[0][2][1][0][0][5]) > 0:
if len(translated[0][2][1][0][0][5][0]) > 0:
text = translated[0][2][1][0][0][5][0][0]
else:
Expand All @@ -138,4 +169,3 @@ def fix_trans_error(translated):
else:
text = translated
return str(text)