Skip to main content

Morphological/Inflection/Lemmatization Engine for Croatian language, POS tagger, stopwords

Project description

Morphological/Inflection/Lemmatization Engine for Croatian language

“text-hr” is Morphological/Inflectional/Lemmatization Engine for Croatian language written in Python programming language. Includes stopwords and Part-Of-Speech tagging engine (POS tagging) based on inverse inflection algorithm for detection.

Since API is not freezed, this project is still in alpha.


Croatian language, lemmatization, stemming, inflection, python, natural language processing (NLP), Part-of-speech (POS) tagging, stopwords, inverse inflection, morphological lexicon


Hrvatski jezik, lematizacija, Python biblioteka, morfologija, infleksija, obrnuta infleksija, prepoznavanje vrsta riječi, računalna obrada govornog jezika, zaustavne riječi, morfološki leksikon


Robert Lujo, Zagreb, Croatia, find mail address in LICENCE


To name the most important:
  • inflection system - for producing all forms of one word
  • detection of word types (POS tagging) - from existing list of word forms
  • list of stopwords

System is based on unicode strings, default codepage to convert from and to string is cp-1250.

Check Getting started.


Installation instructions - if you have installed pip package

pip install text-hr
If not, then do it old-fashioned way:


There are three important parts that this project provides:

Inflection system

Usage example - start python shell:

>>> from text_hr import Verb
>>> v = Verb("platiti")
>>> for k in sorted(v.forms.keys()):
...     print(k, v.forms[k])
AOR/P/1 [u'platismo']
AOR/P/2 [u'platiste']
AOR/P/3 [u'plati\u0161e']
AOR/S/1 [u'platih']
AOR/S/2 [u'plati']
AOR/S/3 [u'plati']
IMP/P/1 [u'platasmo', u'pla\u0107asmo', u'platijasmo']
IMP/P/2 [u'plataste', u'pla\u0107aste', u'platijaste']
IMP/P/3 [u'platahu', u'pla\u0107ahu', u'platijahu']
VA_PA//P_O+S+V+N [u'pla\u0107eno']
X_INF// [u'platiti']
X_VAD_PAS// [u'plativ\u0161i']
X_VAD_PRE// [u'plate\u0107i']
X_VAD_PRE// [u'plate\u0107i']

Detection of word types (POS tagging)

TODO: to be done - check test_detect.txt for samples, and for the logic:

First example in test_detect.txt:

>>> from text_hr.detect import WordTypeRecognizerExample
>>> def test_it(word_list, wt_filter=None, level=2):
...     wdh = WordTypeRecognizerExample(word_list, silent=True)
...     if not wt_filter is None:
...         wdh.detect(wt_filter=wt_filter, level=level)  # e.g. wt_filter=["N"]
...     else:
...         wdh.detect(level=level)  # all word types
...     lines_file = LinesFile()
...     wdh.dump_result(lines_file) # doctest: +NORMALIZE_WHITESPACE +ELLIPSIS
...     print("\n".join(lines_file.lines))
...     return wdh

>>> class LinesFile(object):
...     def __init__(self):
...         self.lines = []
...     def write(self, s):
...         self.lines.append(repr(s.rstrip()))

>>> word_list = [
...   "Broj    84"
... , "broji   34"
... , "Brojila  28"
... , "broje   23"
... , "brojeći 22"
... , "brojim   7"
... , "brojimo  5"
... , "brojiš   4"
... , "brojahu  2"
... , "brojaše  1"
... , "brojite  1"
... , "-brijestovu 1"
... , "brijestovi 1"   #the only one checked with endswith, but all other will be checked with get_freq
... , "-brijestove 1"
... , "-brijestova 1"
... ]

Lowest quality, but fastest
>>> wdh = test_it(word_list, level=4) # doctest: +ELLIPSIS
" 10/  183 -> brojati              (u'V-XX_-_JATI-je\\u0107i-0') 84/broj,34/broji,23/broje,22/broje\xe6i,7/brojim,5/brojimo,4/broji\x9a,2/brojahu,1/brojite,1/broja\x9ae"

List of stopwords

Is located in std_words.txt, and you can read it directly from here

The list can be updated like this:

>>> import text_hr
>>> text_hr.dump_all_std_words()
Totaly 2904 word forms dumped to r:\hg-clones\python\text-hr\text_hr\std_words.txt in codepage utf8

Iteration over all words goes like this:

from text_hr import get_all_std_words

for word_base, l_key, cnt, _suff_id, wform_key, wform in get_all_std_words():
    print(word_base, l_key, cnt, _suff_id, wform_key, wform)


Since there is currently no good documentation, the best source of further information is by reading tests inside of modules and tests in tests directory (dev version). More information in Running tests. You can allways read a source.


Currently there is no documentation. In progress …


Since this project is limited by my free time, support is limited.


If you encounter bug, the best is to report it to the bitbucket web page

If there will be an interest for development for other inflection rich languages, I’d be glad to decouple language specific code and create new project that will be capable to deal with multiple languages.

The best way to contact me is by mail (find in LICENCE).

TODO list is in readme.txt (dev version).


Since this project is not currently in the stable API phase, contribution should wait for a while.


All tests are doctests (not unittests). There are three type of tests in the package:

  1. doctests in each module - e.g. in
  2. doctests in tests/test_*.txt - only development version
  3. tests which are not automatically compared - i.e. in special call mode can produce output file which needs to be compared manually with some existing file. Such test(s) are very slow. This needs to be changed to be automatic.

Running each module directly will run 1. and 2. if running from development version. To get development version To use development version (

hg clone

create text_hr.pth in python site-packages directory with path to text-hr e.g.:

To run all tests:
  • go to tests directory

  • run like (with sample output):

    > python
    testing module   __init__
    testing module   adjectives
    testing textfile R:\hg-clones\python\text-hr\tests\test_adj.txt
    testing textfile R:\hg-clones\python\text-hr\tests\test_verbs_type.txt
To run tests for just one module:
  • goto text_hr directory

  • run tests by running module, e.g.:

    > py
    __main__: running doctests
    ..\tests\test_pronouns.txt: running doctests
  • in the case you’re not running from dev version, you’ll get output like this:

    > py
    __main__: running doctests
    ..\tests\test_pronouns.txt: Not found, skipping


Master thesis pdf in Croatian (134 pages) with title:

Lociranje sličnih logičkih cjelina u tekstualnim
dokumentima na hrvatskome jeziku

can be found at:


various things, see readme.txt for details.



RL 200507
  • migration to python 3+, tested on python 3.7, all tests pass


RL 121210
  • fixed wrong readme on bitbucket homepage


RL 100617
  • utf-8 setup


RL 100617
  • master thesis pdf added to repository (in Croatian, 134 pages)


RL 100617
  • minor changes


RL 100617
  • beta release
  • tags: lemmatization, stemming


RL 100610:
  • text_hr package reorganized ( with __all__ and imports …)
  • removed
  • std_words.txt


RL 100608 :
  • enabled tests from for all
  • enabled tests from directly from each modules


RL 100607:
  • recreated repo at bitbucket
  • no .suff_registry.pickle and testing_*.out put in zip


RL 100605:
  • first installable release

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

text-hr-0.20.tar.gz (96.0 kB view hashes)

Uploaded source

Built Distribution

text_hr-0.20-py3-none-any.whl (97.7 kB view hashes)

Uploaded py3

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Huawei Huawei PSF Sponsor Microsoft Microsoft PSF Sponsor NVIDIA NVIDIA PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page