add language detection, and use JSON to clean up the code for easier comprehension

googletrans/response.py

@@ -0,0 +1,42 @@
+class Translated:
+    """
+    The Translated object, which contains Google Translator's result.
+
+    :param src: source langauge (default: auto)
+    :param dest: destination language (default: en)
+    :param origin: original text
+    :param text: translated text
+    :param pronunciation: the pronunciation provided by Google Translator
+    """
+    def __init__(self, src, dest, origin, text, pronunciation):
+        self.src = src
+        self.dest = dest
+        self.origin = origin
+        self.text = text
+        self.pronunciation = pronunciation
+
+    def __str__(self):
+        return self.__unicode__()
+
+    def __unicode__(self):
+        return u'<Translated src={src} dest={dest} text={text} pronunciation={pronunciation}>'.format(
+            src=self.src, dest=self.dest, text=self.text, pronunciation=self.pronunciation)
+
+class Detected:
+    """
+    The detected object, which contains Google Translator's langauge detection result.
+
+    :param lang: detected language
+    :param confidence: the confidence of detection (0.00 to 1.00)
+    """
+    def __init__(self, lang, confidence):
+        self.lang = lang
+        self.confidence = confidence
+
+    def __str__(self):
+        return self.__unicode__()
+
+    def __unicode__(self):
+        return u'<Detected lang={lang} confidence={confidence}>'.format(
+            lang=self.lang, confidence=self.confidence)
+

googletrans/translator.py

@@ -3,23 +3,6 @@
 A Translation module.
 
 You can translate text using this module.
-
-Basic usage: 
-    >>> from googletrans import 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
 """
 import re
 import requests
@@ -28,7 +11,8 @@ from future.moves.urllib.parse import quote
 
 from . import __version__
 from googletrans import urls
-from googletrans.translated import Translated
+from googletrans.conversion import format_json
+from googletrans.response import Translated, Detected
 
 user_agent = 'PyGt/{0}'.format(__version__)
 
@@ -53,11 +37,27 @@ def agent():
 
     return __agent
 
-# translator.translate(text, to='')
 def translate(text, dest='en', src='auto'):
     """
     Translate the passed text into destination language.
 
+Basic usage: 
+    >>> from googletrans import 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)
@@ -86,23 +86,22 @@ def translate(text, dest='en', src='auto'):
 
     [[["공화국","republique"],[,,"gonghwagug"]],,"fr",,,[["republique",1,[["공화국",1000,true,false],["공화국의",0,true,false],["공화국에",0,true,false],["공화국에서",0,true,false]],[[0,10]],"republique",0,1]],0.94949496,,[["fr"],,[0.94949496]],,,[["명사",[[["communauté","démocratie"],""]],"république"]]]
     """
+    data = format_json(r.text)
 
     # this code will be updated when the format is changed.
-    # (I know this code is not really efficient and so sketchy.)
-    translated = r.text.split('[[[')[1][1:].split('"')[0]
+    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 = RE_SRC.findall(r.text)[0]
+        src = data[-1][0][0]
     except: pass
 
     pron = origin
-    if src not in EXCLUDES:
     try:
-            pron_table = r.text.split('[[[')[1].split('[')[1]
-            pron = pron_table.split('"')[1].split('"')[0]
+        pron = data[0][1][-1]
     except: pass
-    if dest in EXCLUDES:
+    if dest in EXCLUDES and pron == origin:
         pron = translated
 
     # put final values into new Translated object
@@ -110,3 +109,59 @@ def translate(text, dest='en', src='auto'):
         text=translated, pronunciation=pron)
 
     return result
+
+def detect(text):
+    """
+    Detect the language of a text.
+
+Basic usage: 
+    >>> from googletrans import translator
+    >>> translator.detect('이 문장은 한글로 쓰여졌습니다.')
+    <Detected lang=ko confidence=0.27041003>
+    >>> translator.detect('この文章は日本語で書かれました。')
+    <Detected lang=ja confidence=0.64889508>
+    >>> translator.detect('This sentence is written in English.')
+    <Detected lang=en confidence=0.22348526>
+    >>> translator.detect('Tiu frazo estas skribita en Esperanto.')
+    <Detected lang=eo confidence=0.10538048>
+
+Advanced usage:
+    >>> langs = translator.detect(['한국어', '日本語', 'English', 'le français'])
+    >>> for lang in langs:
+    ...    print(lang.lang, lang.confidence)
+    ko 1
+    ja 0.92929292
+    en 0.96954316
+    fr 0.043500196
+
+    :param text: the text you want to detect.
+
+    :rtype: Detected
+    :rtype: list (when list is passed)
+    """
+    if isinstance(text, list):
+        result = []
+        for item in text:
+            lang = detect(item)
+            result.append(lang)
+        return result
+
+    result = ''
+    sess = agent() # acquire requests session
+    origin = text
+    text = quote(text)
+    url = urls.DETECT.format(query=text)
+    r = sess.get(url, headers=__headers)
+    data = format_json(r.text)
+
+    # actual source language that will be recognized by Google Translator when the
+    # src passed is equal to auto.
+    src = ''
+    confidence = 0.0
+    try:
+        src = ''.join(data[-1][0])
+        confidence = data[-1][-1][0]
+    except: pass
+    result = Detected(lang=src, confidence=confidence)
+
+    return result

googletrans/urls.py

@@ -4,3 +4,4 @@ Predefined URLs used to make google translate requests.
 """
 TRANSLATOR = 'https://translate.google.com/'
 TRANSLATE = 'https://translate.google.com/translate_a/single?client=t&sl={src}&tl={dest}&hl={dest}&dt=bd&dt=rm&dt=ss&dt=t&dt=at&ie=UTF-8&oe=UTF-8&q={query}'
+DETECT = 'https://translate.google.com/translate_a/single?client=t&sl=auto&tl=en&hl=en&dt=bd&ie=UTF-8&oe=UTF-8&q={query}'

tests.py

@@ -1,11 +1,16 @@
 # -*- coding: utf-8 -*-
 import unittest
-from googletrans import translator
+from googletrans import translator, conversion
 
 class TranslateTests(unittest.TestCase):
     def setUp(self):
         pass
 
+    def test_to_json(self):
+        text = '[,,"en",,,,0.96954316,,[["en"],,[0.96954316]]]'
+        approx = [None, None, 'en', None, None, None, 0.96954316, None, [['en'], None, [0.96954316]]]
+        assert conversion.format_json(text) == approx
+
     def test_latin_to_english(self):
         result = translator.translate('veritas lux mea', src='la', dest='en')
         assert result.text == 'The truth is my light'
@@ -22,5 +27,12 @@ class TranslateTests(unittest.TestCase):
         assert translations[1].text == u'이상 점프'
         assert translations[2].text == u'게으른 개'
 
+    def test_language_detection(self):
+        ko = translator.detect('한국어')
+        assert ko.lang == 'ko'
+
+        en = translator.detect('English')
+        assert en.lang == 'en'
+
 if __name__ == '__main__':
     unittest.main()

translate

@@ -11,8 +11,19 @@ def main():
         help='The destination language you want to translate. (Default: en)')
     parser.add_argument('-s', '--src', default='auto',
         help='The source language you want to translate. (Default: auto)')
+    parser.add_argument('-c', '--detect', action='store_true', default=False,
+        help='')
     args = parser.parse_args()
 
+    if args.detect:
+        result = translator.detect(args.text)
+        result = """
+[{lang}, {confidence}] {text}
+        """.strip().format(text=args.text,
+            lang=result.lang, confidence=result.confidence)
+        print(result)
+        return
+
     result = translator.translate(args.text, dest=args.dest, src=args.src)
     result = """
 [{src}] {original}