CHANGELOG.md
CONTRIBUTING.md
LICENSE
MANIFEST.in
README.md
pyproject.toml
.github/workflows/ci.yml
.github/workflows/release.yml
examples/README.md
examples/__init__.py
examples/alignment_ner.py
examples/basic_usage.py
examples/cache_usage.py
examples/custom_configuration.py
examples/lemmatization.py
examples/metrics_and_validation.py
examples/morpheme_splitting.py
examples/normalization_tests.py
examples/pipeline_custom.py
examples/pos_tagging.py
examples/run_all.py
examples/script_detection.py
examples/sentence_split.py
examples/stemming.py
examples/stopwords_filtering.py
examples/tokenization.py
examples/validation_quality.py
src/tajiknlp/__init__.py
src/tajiknlp/config.py
src/tajiknlp/errors.py
src/tajiknlp/schemas.py
src/tajiknlp.egg-info/PKG-INFO
src/tajiknlp.egg-info/SOURCES.txt
src/tajiknlp.egg-info/dependency_links.txt
src/tajiknlp.egg-info/requires.txt
src/tajiknlp.egg-info/top_level.txt
src/tajiknlp/alignment/__init__.py
src/tajiknlp/alignment/builder.py
src/tajiknlp/alignment/spans.py
src/tajiknlp/components/__init__.py
src/tajiknlp/components/cleaners/__init__.py
src/tajiknlp/components/cleaners/text_cleaner.py
src/tajiknlp/components/embeddings/__init__.py
src/tajiknlp/components/embeddings/static.py
src/tajiknlp/components/filters/__init__.py
src/tajiknlp/components/filters/stopwords.py
src/tajiknlp/components/lemmatizers/__init__.py
src/tajiknlp/components/lemmatizers/base.py
src/tajiknlp/components/lemmatizers/dictionary.py
src/tajiknlp/components/normalizers/__init__.py
src/tajiknlp/components/normalizers/base.py
src/tajiknlp/components/normalizers/cyrillic.py
src/tajiknlp/components/sentencizers/__init__.py
src/tajiknlp/components/sentencizers/regex_sentencizer.py
src/tajiknlp/components/stemmers/__init__.py
src/tajiknlp/components/stemmers/tajik_stemmer.py
src/tajiknlp/components/taggers/__init__.py
src/tajiknlp/components/taggers/ml.py
src/tajiknlp/components/taggers/rule_based.py
src/tajiknlp/components/tokenizers/__init__.py
src/tajiknlp/components/tokenizers/base.py
src/tajiknlp/components/tokenizers/morpheme.py
src/tajiknlp/components/tokenizers/regex.py
src/tajiknlp/core/__init__.py
src/tajiknlp/core/base.py
src/tajiknlp/data/lemmas_dict_v0.1.json
src/tajiknlp/data/pos_tags.json
src/tajiknlp/data/preffix_rules.json
src/tajiknlp/data/stopwords.json
src/tajiknlp/data/suffix_rules.json
src/tajiknlp/data/tajik_pos.jsonl
src/tajiknlp/pipeline/__init__.py
src/tajiknlp/pipeline/builder.py
src/tajiknlp/pipeline/pipeline.py
src/tajiknlp/resources/__init__.py
src/tajiknlp/resources/cache.py
src/tajiknlp/resources/hub.py
src/tajiknlp/utils/__init__.py
src/tajiknlp/utils/metrics.py
src/tajiknlp/utils/script_detector.py
src/tajiknlp/utils/validation.py
tests/__init__.py
tests/conftest.py
tests/test_basic.py
tests/test_config.py
tests/test_errors.py
tests/test_metrics.py
tests/test_schemas.py
tests/test_validation.py
tests/alignment/__init__.py
tests/alignment/test_alignment.py
tests/components/__init__.py
tests/components/test_cleaners.py
tests/components/test_lemmatizers.py
tests/components/test_normalizers.py
tests/components/test_sentencizers.py
tests/components/test_stemmers.py
tests/components/test_tokenizers.py
tests/pipeline/__init__.py
tests/pipeline/test_pipeline.py
tests/resources/test_cache.py
tests/utils/__init__.py
tests/utils/metrics.py
tests/utils/test_script_detector.py