Adawat is a toolkit which provides multiple functions as:

• Tashkeel
  • tashkeel : vocalize text, we recomand to use mishkal-console instead.
  • tashkeel with suggestions for every word.
  • reduce : strip unnecessary tashkeel from avocalized text
  • strip : remove all harakat and shadda
  • compare : Compare Tashkeel between input text and the automatic vocalized text
• Transformation and Converion
  • romanize : convert an arabic script text to latin representation
  • arabize : convert an transliterated arabic script text to arabic
  • inverse : inverse text
  • numbers to words : convert numeric value to words
  • normalize : normalize letters in arabic text
  • unshape : unshape arabic letters
• Analysis and generation
  • stem : morphology analysis of given texts
  • tokenize : tokenize a text to words
  • wordtag : classify words into (nouns, verbs, stopwords)
  • affixate : generate all word forms by affixation
• Extraction
  • collocation : extract collocations from text
  • language : detect arabic and latin clauses in text
  • named : extract named enteties from text
  • numbered : extarct numbred clauses from text
• Divers
  • affixate : generate all word forms by affixation
  • poetry : format poetry texts to columns poetry
  • random : get a random text