def is_valid_lang_name(lang):
"""
Return True if given language name in English exists in polyglot library; False otherwise.
:param lang: str (language name in English)
:return: bool
"""
return lang.title() in Detector.supported_languages()
# -*- encoding: utf-8 -*-
from polyglot.detect import Detector
arabic_text = u"""
أفاد مصدر امني في قيادة عمليات صلاح الدين في العراق بأن " القوات الامنية تتوقف لليوم
الثالث على التوالي عن التقدم الى داخل مدينة تكريت بسبب
انتشار قناصي التنظيم الذي يطلق على نفسه اسم "الدولة الاسلامية" والعبوات الناسفة
والمنازل المفخخة والانتحاريين، فضلا عن ان القوات الامنية تنتظر وصول تعزيزات اضافية ".
"""
detector = Detector(arabic_text)
print detector.language
mixed_text = u"""
China (simplified Chinese: 中国; traditional Chinese: 中國),
officially the People's Republic of China (PRC), is a sovereign state located in East Asia.
"""
for language in Detector(mixed_text).languages:
print language
'''
detector = Detector("pizza")
print(detector)
print(Detector("4"))
'''
from polyglot.utils import pretty_list
print(pretty_list(Detector.supported_languages()))
print("\nDerivational Morphemes using polyglot library")
for w in words_derv:
w = Word(w, language="en")
print("{:<20}{}".format(w, w.morphemes))
print("\nInflectional Morphemes using polyglot library")
for w in word_infle:
w = Word(w, language="en")
print("{:<20}{}".format(w, w.morphemes))
print("\nSome Morphemes examples using polyglot library")
for w in words:
w = Word(w, language="en")
print("{:<20}{}".format(w, w.morphemes))
mixed_text = u"""
China (simplified Chinese: 中国; traditional Chinese: 中國),
officially the People's Republic of China (PRC), is a sovereign state located in East Asia.
"""
if __name__ == "__main__":
stemmer_porter()
polyglot_stem()
print("\n----------")
for language in Detector(mixed_text).languages:
print(language)
print("\n----------")
print(Detector.supported_languages())
def supported_languages(input_text):
return (pretty_list(Detector.supported_languages()))
def supported_languages():
if input_text.supported_language:
print(pretty_list(Detector.supported_languages()))
