Skip to content

ruMorph

ruMorph

ruMorph is a morphological analyzer of Russian: a Rust core with a Python API. For a word form the analyzer finds its analyses in the OpenCorpora dictionary - the initial form (lemma), the part of speech and the Universal Dependencies features - orders them by probability and builds the forms of the word.

Early version

Before 1.0 the API may change between 0.x versions, changes are described in the release notes.

Features

  • Analysis

    Lemma, UD part of speech and features, probability of the analysis; lists of words and lemmatization without the GIL

    Analyzer

  • Universal Dependencies

    Parts of speech, features and lemmas in the SynTagRus conventions; numbers, punctuation and Latin words by rules, unknown words by their ending

    Word analysis

  • Inflection

    Forms of the lexeme, the form by UD features, agreement with a number

    Inflection

  • Migrating from pymorphy

    Correspondence of pymorphy2 and pymorphy3 calls, parts of speech and grammemes

    Migrating from pymorphy

  • Speed and memory

    Analysis, lemmatization and inflection compared with pymorphy3, dictionary loading and memory

    Speed and memory

  • Exceptions

    Built-in Python exceptions and FormNotFoundError for missing forms

    Exceptions

Installation

Python 3.11 or newer is required.

pip install rumorph

Prebuilt wheels and building from source are described on the Installation page.

Quick start

from rumorph import Analyzer

morph = Analyzer()
morph.lemmatize(["Мы", "стали", "друзьями"])
[(a.lemma, a.pos, a.feats.get("Case"), round(a.prob, 3)) for a in morph.analyze("стали")][:2]
cat = morph.analyze("кошка")[0]
cat.inflect(Case="Gen", Number="Plur"), morph.analyze("рубль")[0].agree(5)

['мы', 'стать', 'друг']
[('стать', 'VERB', None, 0.975), ('сталь', 'NOUN', 'Gen', 0.011)]
('кошек', 'рублей')
Project structure
  • crates/rumorph - the Rust core of the analyzer: dictionary format, building, analysis and inflection
  • crates/rumorph-build - building the dictionary from the pymorphy3-dicts-ru export and converting OpenCorpora tags to UD
  • crates/rumorph-py - the Python module rumorph._rumorph on PyO3
  • python/rumorph - the Python package
  • scripts - exporting the pymorphy3-dicts-ru dictionary
  • docs - MkDocs documentation in Russian and English
  • tests - tests of the Python package