def test_translate(self, Translator):
page = create_test_page(
title="Test page",
slug="test-page",
test_charfield="Some translatable content",
test_richtextfield="<p>Translatable <b>rich text</b></p>",
)
request_page = self.add_page_to_request(page)
# Mock response from Google Translate
Translator().translate.return_value = [
Translated(
"en",
"fr",
"Some translatable content",
"Certains contenus traduisibles",
"Certains contenus traduisibles",
),
Translated(
"en",
"fr",
"Translatable rich text",
"Texte riche traduisible",
"Texte riche traduisible",
),
]
response = self.client.post(
reverse(
"wagtail_localize_google_translate:translate",
args=[self.translation_request.id],
),
{"publish": "on"},
)
self.assertRedirects(
response,
reverse(
"wagtail_localize_workflow_management:detail",
args=[self.translation_request.id],
),
)
Translator().translate.assert_called_with(
["Some translatable content", "Translatable rich text"], dest="fr", src="en"
)
request_page.refresh_from_db()
self.assertTrue(request_page.is_completed)
translated_page = page.get_translation(Locale.objects.get(language_code="fr"))
self.assertTrue(translated_page.live)
self.assertEqual(
translated_page.test_charfield, "Certains contenus traduisibles"
)
self.assertEqual(
translated_page.test_richtextfield, "<p>Texte riche traduisible</p>"
)
def test_translate_with_nested_snippet(self, Translator):
snippet = TestSnippet.objects.create(field="Some test snippet content")
page = create_test_page(
title="Test page", slug="test-page", test_snippet=snippet
)
request_page = self.add_page_to_request(page)
# Mock response from Google Translate
Translator().translate.return_value = [
Translated(
"en",
"fr",
"Some test snippet content",
"Du contenu d'extrait de test",
"Du contenu d'extrait de test",
)
]
response = self.client.post(
reverse(
"wagtail_localize_google_translate:translate",
args=[self.translation_request.id],
),
{"publish": "on"},
)
self.assertRedirects(
response,
reverse(
"wagtail_localize_workflow_management:detail",
args=[self.translation_request.id],
),
)
Translator().translate.assert_called_with(
["Some test snippet content"], dest="fr", src="en"
)
request_page.refresh_from_db()
self.assertTrue(request_page.is_completed)
translated_page = page.get_translation(Locale.objects.get(language_code="fr"))
self.assertEqual(
translated_page.test_snippet.field, "Du contenu d'extrait de test"
)
def translate(self, text, dest='en', src='auto'):
dest = dest.lower().split('_', 1)[0]
src = src.lower().split('_', 1)[0]
origin = text
data = self._translate(text, dest, src, None)
# this code will be updated when the format is changed. / Googletrans Author note
translated = ''.join([d[0] if d[0] else '' for d in data[0]])
pron = 'No pronunciation'
if data[0][1][-1] is not None:
pron = data[0][1][-1]
return Translated(src=src,
dest=dest,
origin=origin,
text=translated,
pronunciation=pron)
def translate(self, text, dest='en', src='auto', **kwargs):
"""Translate text from source language to destination language
:param text: The source text(s) to be translated. Batch translation is supported via sequence input.
:type text: UTF-8 :class:`str`; :class:`unicode`; string sequence (list, tuple, iterator, generator)
:param dest: The language to translate the source text into.
The value should be one of the language codes listed in :const:`googletrans.LANGUAGES`
or one of the language names listed in :const:`googletrans.LANGCODES`.
:param dest: :class:`str`; :class:`unicode`
:param src: The language of the source text.
The value should be one of the language codes listed in :const:`googletrans.LANGUAGES`
or one of the language names listed in :const:`googletrans.LANGCODES`.
If a language is not specified,
the system will attempt to identify the source language automatically.
:param src: :class:`str`; :class:`unicode`
:rtype: Translated
:rtype: :class:`list` (when a list is passed)
Basic usage:
>>> from googletrans import Translator
>>> translator = Translator()
>>> translator.translate('안녕하세요.')
<Translated src=ko dest=en text=Good evening. pronunciation=Good evening.>
>>> translator.translate('안녕하세요.', dest='ja')
<Translated src=ko dest=ja text=こんにちは。 pronunciation=Kon'nichiwa.>
>>> translator.translate('veritas lux mea', src='la')
<Translated src=la dest=en text=The truth is my light pronunciation=The truth is my light>
Advanced usage:
>>> translations = translator.translate(['The quick brown fox', 'jumps over', 'the lazy dog'], dest='ko')
>>> for translation in translations:
... print(translation.origin, ' -> ', translation.text)
The quick brown fox -> 빠른 갈색 여우
jumps over -> 이상 점프
the lazy dog -> 게으른 개
"""
dest = dest.lower().split('_', 1)[0]
src = src.lower().split('_', 1)[0]
if src != 'auto' and src not in LANGUAGES:
if src in SPECIAL_CASES:
src = SPECIAL_CASES[src]
elif src in LANGCODES:
src = LANGCODES[src]
else:
raise ValueError('invalid source language')
if dest not in LANGUAGES:
if dest in SPECIAL_CASES:
dest = SPECIAL_CASES[dest]
elif dest in LANGCODES:
dest = LANGCODES[dest]
else:
raise ValueError('invalid destination language')
if isinstance(text, list):
result = []
for item in text:
translated = self.translate(item, dest=dest, src=src, **kwargs)
result.append(translated)
return result
origin = text
data = self._translate(text, dest, src, kwargs)
# this code will be updated when the format is changed.
translated = ''.join([d[0] if d[0] else '' for d in data[0]])
extra_data = self._parse_extra_data(data)
# actual source language that will be recognized by Google Translator when the
# src passed is equal to auto.
try:
src = data[2]
except Exception: # pragma: nocover
pass
pron = origin
try:
pron = data[0][1][-2]
except Exception: # pragma: nocover
pass
if pron is None:
try:
pron = data[0][1][2]
except: # pragma: nocover
pass
if dest in EXCLUDES and pron == origin:
pron = translated
# put final values into a new Translated object
result = Translated(src=src,
dest=dest,
origin=origin,
text=translated,
pronunciation=pron,
extra_data=extra_data)
return result
def translate(self, text, dest='en', src='auto'):
"""Translate text from source language to destination language
:param text: The source text(s) to be translated. Batch translation is supported via sequence input.
:type text: UTF-8 :class:`str`; :class:`unicode`; string sequence (list, tuple, iterator, generator)
:param dest: The language to translate the source text into.
The value should be one of the language codes listed in :const:`googletrans.LANGUAGES`.
:param dest: :class:`str`; :class:`unicode`
:param src: The language of the source text.
The value should be one of the language codes listed in :const:`googletrans.LANGUAGES`.
If a language is not specified,
the system will attempt to identify the source language automatically.
:param src: :class:`str`; :class:`unicode`
:rtype: Translated
:rtype: :class:`list` (when a list is passed)
Basic usage:
>>> from googletrans import Translator
>>> translator = Translator()
>>> translator.translate('안녕하세요.')
<Translated src=ko dest=en text=Good evening. pronunciation=Good evening.>
>>> translator.translate('안녕하세요.', dest='ja')
<Translated src=ko dest=ja text=こんにちは。 pronunciation=Kon'nichiwa.>
>>> translator.translate('veritas lux mea', src='la')
<Translated src=la dest=en text=The truth is my light pronunciation=The truth is my light>
Advanced usage:
>>> translations = translator.translate(['The quick brown fox', 'jumps over', 'the lazy dog'], dest='ko')
>>> for translation in translations:
... print(translation.origin, ' -> ', translation.text)
The quick brown fox -> 빠른 갈색 여우
jumps over -> 이상 점프
the lazy dog -> 게으른 개
"""
if isinstance(text, list):
result = []
for item in text:
translated = self.translate(item, dest=dest, src=src)
result.append(translated)
return result
origin = text
data = self._translate(text, dest, src)
# this code will be updated when the format is changed.
translated = ''.join([d[0] if d[0] else '' for d in data[0]])
# actual source language that will be recognized by Google Translator when the
# src passed is equal to auto.
try:
src = data[-1][0][0]
except Exception: # pragma: nocover
pass
pron = origin
try:
pron = data[0][1][-1]
except Exception: # pragma: nocover
pass
if not PY3 and isinstance(pron, unicode) and isinstance(
origin, str): # pragma: nocover
origin = origin.decode('utf-8')
if dest in EXCLUDES and pron == origin:
pron = translated
# for python 2.x compatbillity
if not PY3: # pragma: nocover
if isinstance(src, str):
src = src.decode('utf-8')
if isinstance(dest, str):
dest = dest.decode('utf-8')
if isinstance(translated, str):
translated = translated.decode('utf-8')
# put final values into a new Translated object
result = Translated(src=src,
dest=dest,
origin=origin,
text=translated,
pronunciation=pron)
return result
async def translate(self, text: str, dest='en', src='auto'):
dest = dest.lower().split('_', 1)[0]
src = src.lower().split('_', 1)[0]
if src != 'auto' and src not in LANGUAGES:
if src in SPECIAL_CASES:
src = SPECIAL_CASES[src]
elif src in LANGCODES:
src = LANGCODES[src]
else:
raise ValueError('invalid source language')
if dest not in LANGUAGES:
if dest in SPECIAL_CASES:
dest = SPECIAL_CASES[dest]
elif dest in LANGCODES:
dest = LANGCODES[dest]
else:
raise ValueError('invalid destination language')
origin = text
data, response = await self._translate(text, dest, src)
token_found = False
square_bracket_counts = [0, 0]
resp = ''
for line in data.split('\n'):
token_found = token_found or f'"{RPC_ID}"' in line[:30]
if not token_found:
continue
is_in_string = False
for index, char in enumerate(line):
if char == '\"' and line[max(0, index - 1)] != '\\':
is_in_string = not is_in_string
if not is_in_string:
if char == '[':
square_bracket_counts[0] += 1
elif char == ']':
square_bracket_counts[1] += 1
resp += line
if square_bracket_counts[0] == square_bracket_counts[1]:
break
data = json.loads(resp)
parsed = json.loads(data[0][2])
# not sure
should_spacing = parsed[1][0][0][3]
translated_parts = list(map(lambda part: TranslatedPart(part[0], part[1] if len(part) >= 2 else []), parsed[1][0][0][5]))
translated = (' ' if should_spacing else '').join(map(lambda part: part.text, translated_parts))
if src == 'auto':
try:
src = parsed[2]
except:
pass
if src == 'auto':
try:
src = parsed[0][2]
except:
pass
# currently not available
confidence = None
origin_pronunciation = None
try:
origin_pronunciation = parsed[0][0]
except:
pass
pronunciation = None
try:
pronunciation = parsed[1][0][0][1]
except:
pass
extra_data = {
'confidence': confidence,
'parts': translated_parts,
'origin_pronunciation': origin_pronunciation,
'parsed': parsed,
}
result = Translated(src=src, dest=dest, origin=origin,
text=translated, pronunciation=pronunciation,
parts=translated_parts,
extra_data=extra_data,
response=response)
return result
def translate(self, text: str, dest='en', src='auto'):
"""Translate text from source language to destination language
:param text: The source text(s) to be translated. Batch translation is supported via sequence input.
:type text: UTF-8 :class:`str`; :class:`unicode`; string sequence (list, tuple, iterator, generator)
:param dest: The language to translate the source text into.
The value should be one of the language codes listed in :const:`googletrans.LANGUAGES`
or one of the language names listed in :const:`googletrans.LANGCODES`.
:param dest: :class:`str`; :class:`unicode`
:param src: The language of the source text.
The value should be one of the language codes listed in :const:`googletrans.LANGUAGES`
or one of the language names listed in :const:`googletrans.LANGCODES`.
If a language is not specified,
the system will attempt to identify the source language automatically.
:param src: :class:`str`; :class:`unicode`
:rtype: Translated
:rtype: :class:`list` (when a list is passed)
Basic usage:
>>> from googletrans import Translator
>>> translator = Translator()
>>> translator.translate('안녕하세요.')
<Translated src=ko dest=en text=Good evening. pronunciation=Good evening.>
>>> translator.translate('안녕하세요.', dest='ja')
<Translated src=ko dest=ja text=こんにちは。 pronunciation=Kon'nichiwa.>
>>> translator.translate('veritas lux mea', src='la')
<Translated src=la dest=en text=The truth is my light pronunciation=The truth is my light>
Advanced usage:
>>> translations = translator.translate(['The quick brown fox', 'jumps over', 'the lazy dog'], dest='ko')
>>> for translation in translations:
... print(translation.origin, ' -> ', translation.text)
The quick brown fox -> 빠른 갈색 여우
jumps over -> 이상 점프
the lazy dog -> 게으른 개
"""
dest = dest.lower().split('_', 1)[0]
src = src.lower().split('_', 1)[0]
if src != 'auto' and src not in LANGUAGES:
if src in SPECIAL_CASES:
src = SPECIAL_CASES[src]
elif src in LANGCODES:
src = LANGCODES[src]
else:
raise ValueError('invalid source language')
if dest not in LANGUAGES:
if dest in SPECIAL_CASES:
dest = SPECIAL_CASES[dest]
elif dest in LANGCODES:
dest = LANGCODES[dest]
else:
raise ValueError('invalid destination language')
origin = text
data, response = self._translate(text, dest, src)
token_found = False
square_bracket_counts = [0, 0]
resp = ''
for line in data.split('\n'):
token_found = token_found or f'"{RPC_ID}"' in line[:30]
if not token_found:
continue
is_in_string = False
for index, char in enumerate(line):
if char == '\"' and line[max(0, index - 1)] != '\\':
is_in_string = not is_in_string
if not is_in_string:
if char == '[':
square_bracket_counts[0] += 1
elif char == ']':
square_bracket_counts[1] += 1
resp += line
if square_bracket_counts[0] == square_bracket_counts[1]:
break
data = json.loads(resp)
parsed = json.loads(data[0][2])
# not sure
should_spacing = parsed[1][0][0][3]
translated_parts = None
translated = None
try:
translated_parts = list(
map(
lambda part: TranslatedPart(
part[0], part[1]
if len(part) >= 2 else []), parsed[1][0][0][5]))
except TypeError:
translated_parts = [
TranslatedPart(parsed[1][0][1][0],
[parsed[1][0][0][0], parsed[1][0][1][0]])
]
translated = (' ' if should_spacing else '').join(
map(lambda part: part.text, translated_parts))
if src == 'auto':
try:
src = parsed[2]
except TypeError:
pass
if src == 'auto':
try:
src = parsed[0][2]
except TypeError:
pass
# currently not available
confidence = None
origin_pronunciation = None
try:
origin_pronunciation = parsed[0][0]
except TypeError:
pass
pronunciation = None
try:
pronunciation = parsed[1][0][0][1]
except TypeError:
pass
mistake = None
try:
mistake = parsed[0][1][0][0][1]
except TypeError:
pass
extra_data = {
'confidence': confidence,
'parts': translated_parts,
'possible-mistakes': [mistake,
utils.strip_html_tags(mistake)],
'src-pronunciation': origin_pronunciation,
'parsed': parsed,
}
result = Translated(src=src,
dest=dest,
origin=origin,
text=translated,
pronunciation=pronunciation,
parts=translated_parts,
extra_data=extra_data,
response=response)
return result
def translate(self, text, dest='en', src='auto'):
"""
Translate the passed text into destination language.
Basic usage:
>>> from googletrans import Translator
>>> translator = Translator()
>>> translator.translate('안녕하세요.')
<Translated src=ko dest=en text=Good evening. pronunciation=Good evening.>
>>> translator.translate('안녕하세요.', dest='ja')
<Translated src=ko dest=ja text=こんにちは。 pronunciation=Kon'nichiwa.>
>>> translator.translate('veritas lux mea', src='la')
<Translated src=la dest=en text=The truth is my light pronunciation=The truth is my light>
Advanced usage:
>>> translations = translator.translate(['The quick brown fox', 'jumps over', 'the lazy dog'], dest='ko')
>>> for translation in translations:
... print(translation.origin, ' -> ', translation.text)
The quick brown fox -> 빠른 갈색 여우
jumps over -> 이상 점프
the lazy dog -> 게으른 개
:param text: the text you want to translate.
you can pass this parameter as a list object, as shown in the advanced usage above.
:param dest: the destination language you want to translate. (default: en)
:param src: the source language you want to translate. (default: auto)
:rtype: Translated
:rtype: list (when list is passed)
"""
if isinstance(text, list):
result = []
for item in text:
translated = self.translate(item, dest=dest, src=src)
result.append(translated)
return result
origin = text
data = self._translate(text, dest, src)
# this code will be updated when the format is changed.
translated = data[0][0][0]
# actual source language that will be recognized by Google Translator when the
# src passed is equal to auto.
try:
src = data[-1][0][0]
except Exception: # pragma: nocover
pass
pron = origin
try:
pron = data[0][1][-1]
except Exception: # pragma: nocover
pass
if not PY3 and isinstance(pron, unicode) and isinstance(
origin, str): # pragma: nocover
origin = origin.decode('utf-8')
if dest in EXCLUDES and pron == origin:
pron = translated
# for python 2.x compatbillity
if not PY3: # pragma: nocover
if isinstance(src, str):
src = src.decode('utf-8')
if isinstance(dest, str):
dest = dest.decode('utf-8')
if isinstance(translated, str):
translated = translated.decode('utf-8')
# put final values into a new Translated object
result = Translated(src=src,
dest=dest,
origin=origin,
text=translated,
pronunciation=pron)
return result