LICENSE
README.md
pyproject.toml
requirements.txt
setup.py
impresso_essentials/__init__.py
impresso_essentials/text_utils.py
impresso_essentials/utils.py
impresso_essentials.egg-info/PKG-INFO
impresso_essentials.egg-info/SOURCES.txt
impresso_essentials.egg-info/dependency_links.txt
impresso_essentials.egg-info/requires.txt
impresso_essentials.egg-info/top_level.txt
impresso_essentials/bbox_visualizer/__init__.py
impresso_essentials/bbox_visualizer/get_bbox.py
impresso_essentials/bbox_visualizer/json_builder.py
impresso_essentials/io/__init__.py
impresso_essentials/io/fs_utils.py
impresso_essentials/io/s3.py
impresso_essentials/io/s3_add_provider.py
impresso_essentials/io/s3_delete.py
impresso_essentials/io/s3_set_timestamp.py
impresso_essentials/schemas/LICENSE
impresso_essentials/schemas/Makefile
impresso_essentials/schemas/Pipfile
impresso_essentials/schemas/Pipfile.lock
impresso_essentials/schemas/README.md
impresso_essentials/schemas/requirements.txt
impresso_essentials/schemas/json/canonical/audio_record.schema.json
impresso_essentials/schemas/json/canonical/issue.schema.json
impresso_essentials/schemas/json/canonical/page.schema.json
impresso_essentials/schemas/json/embeddings/embeddings-chunks.schema.json
impresso_essentials/schemas/json/embeddings/embeddings-docs-backup.schema.json
impresso_essentials/schemas/json/embeddings/embeddings-docs.schema.json
impresso_essentials/schemas/json/embeddings/embeddings-entities.schema.json
impresso_essentials/schemas/json/embeddings/embeddings-sentence.schema.json
impresso_essentials/schemas/json/entities/entities-backup.schema.json
impresso_essentials/schemas/json/entities/entities.schema.json
impresso_essentials/schemas/json/image_classification/image_classification.schema.json
impresso_essentials/schemas/json/image_embeddings/image_embeddings.schema.json
impresso_essentials/schemas/json/language_identification/language_identification.schema.json
impresso_essentials/schemas/json/linguistic_annotation/ling_spacy.schema.json
impresso_essentials/schemas/json/linguistic_annotation/lingproc.v2.schema.json
impresso_essentials/schemas/json/ocr_qa/ocr_qa.schema.json
impresso_essentials/schemas/json/rebuilt/audio_record_contentitem.schema.json
impresso_essentials/schemas/json/rebuilt/paper_contentitem.schema.json
impresso_essentials/schemas/json/text_reuse/cluster.schema.json
impresso_essentials/schemas/json/text_reuse/passage.schema.json
impresso_essentials/schemas/json/topic_model/topic_assignment.schema.json
impresso_essentials/schemas/json/topic_model/topic_assignment.v2.schema.json
impresso_essentials/schemas/json/topic_model/topic_description.schema.json
impresso_essentials/schemas/json/versioning/manifest.schema.json
impresso_essentials/schemas/json/visualizer/bbox_visualizer.schema.json
impresso_essentials/versioning/__init__.py
impresso_essentials/versioning/aggregators.py
impresso_essentials/versioning/compute_manifest.py
impresso_essentials/versioning/data_manifest.py
impresso_essentials/versioning/data_statistics.py
impresso_essentials/versioning/git_utils.py
impresso_essentials/versioning/helpers.py
tests/test_text_utils.py