README.md

Setup

python setup.py install or pip install .

Usage

• From python scripts

  >>> from segmentation import segmenter
  >>> input_text = '''
      কাজী মুহম্মদ ওয়াজেদের একমাত্র পুত্র ছিলেন এ. কে. ফজলুক হক। A. K. Fazlul Huq (Sher-E-Bangla) was born into a middle class Bengali Muslim family in Bakerganj, Barisal, Bangladesh in 1873. 
  '''
  >>> segmenter.segment_text(input_text)
  ['কাজী মুহম্মদ ওয়াজেদের একমাত্র পুত্র ছিলেন এ. কে. ফজলুক হক।',
  'A. K. Fazlul Huq (Sher-E-Bangla) was born into a middle class Bengali Muslim family in Bakerganj, Barisal, Bangladesh in 1873.']

  If you don't want a linebreak to be an explicit new line marker, use the following

  >>> segmenter.segment_text(input_text, mode='multi') 

  • Note: the above snippets run with most of the default options, for more advanced options, refer to the terminal script.

• From terminal

  segmenter --help