Fork me on GitHub


Use adhtools for analyzing Arabic corpora.

353 commits | Last update: July 09, 2019

Cite this software

Choose a version:
[[ releases.length > 0 ? releases[selectedIndex].doi : conceptDOI ]]
Copy to clipboard
Choose a citation style:
Download file

What adhtools can do for you

  • Create a BlackLab index of your corpus
  • Works on text files in OpenITI format
  • Use SAFAR's stemmers and morphological analyzers

Adhtools can be used to process corpora of OpenITI text files, together with the corpus metadata. There are workflows for creating BlackLab indices and notebooks with various analyses. The workflows are built on top of nlppln. The tools use SAFAR for morphological analyses of Arabic. Unfortunately, SAFAR is not properly licensed so we don't distribute it with our code, and it needs to be downloaded separately in order to run the workflows.

Read more
  • Text analysis & natural language processing
  • Visualization
  • Workflow technologies
Programming Language
  • Python
  • Apache-2.0
Source code

Participating organizations


  • Dafne van Kuppevelt
    Netherlands eScience Center
  • Janneke van der Zwaan
    Netherlands eScience Center