├── .gitignore ├── CONTRIBUTING.rst ├── COPYING ├── Makefile ├── README.rst ├── doc ├── Makefile ├── _static │ ├── Pipeline_architecture.png │ ├── PyPLNcluster.png │ ├── default-pipeline.png │ ├── logo_pypln.png │ └── pypln.png ├── conf.py ├── data.rst ├── images-source │ ├── Pipeline_architecture.graphml │ ├── PyPLNcluster.graphml │ ├── default-pipeline.dot │ ├── logo_pypln.svg │ └── pypln.graphml ├── index.rst ├── installation.rst ├── intro.rst ├── logo_pypln.svg ├── make.bat ├── parsing.rst ├── storage.rst └── text_extraction.rst ├── make-docs.sh ├── pypln ├── __init__.py └── backend │ ├── __init__.py │ ├── celery_app.py │ ├── celery_task.py │ ├── config.py │ ├── settings.ini.sample │ └── workers │ ├── __init__.py │ ├── bigrams.py │ ├── elastic_indexer.py │ ├── extractor.py │ ├── freqdist.py │ ├── lemmatizer_pt.py │ ├── palavras_noun_phrase.py │ ├── palavras_raw.py │ ├── palavras_semantic_tagger.py │ ├── pos │ ├── __init__.py │ ├── en_nltk.py │ └── pt_palavras.py │ ├── spellchecker.py │ ├── statistics.py │ ├── tokenizer.py │ ├── trigrams.py │ └── word_cloud.py ├── requirements ├── development.txt └── production.txt ├── run_celery.sh ├── scripts ├── add_pipelines.py ├── create_fake_measures.py ├── mongo2sphinx.py └── sphinx.conf ├── setup.py └── tests ├── __init__.py ├── data ├── Mathmodels.rdf ├── encoding_unknown_to_libmagic.txt ├── mixed_encoding_not_detected_by_libmagic_or_chardet ├── pypln.conf ├── random_file ├── test.html ├── test.pdf ├── test.txt ├── test_html_entities.txt └── test_iso-8859-1.txt ├── test_celery_task.py ├── test_elastic_indexer.py ├── test_worker_bigrams.py ├── test_worker_extractor.py ├── test_worker_freqdist.py ├── test_worker_lemmatizer_pt.py ├── test_worker_palavras_noun_phrase.py ├── test_worker_palavras_raw.py ├── test_worker_palavras_semantic_tagger.py ├── test_worker_pos.py ├── test_worker_pos_pt_palavras.py ├── test_worker_spellchecker.py ├── test_worker_statistics.py ├── test_worker_tokenizer.py ├── test_worker_trigrams.py ├── test_worker_wordcloud.py └── utils.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/.gitignore -------------------------------------------------------------------------------- /CONTRIBUTING.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/CONTRIBUTING.rst -------------------------------------------------------------------------------- /COPYING: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/COPYING -------------------------------------------------------------------------------- /Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/Makefile -------------------------------------------------------------------------------- /README.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/README.rst -------------------------------------------------------------------------------- /doc/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/doc/Makefile -------------------------------------------------------------------------------- /doc/_static/Pipeline_architecture.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/doc/_static/Pipeline_architecture.png -------------------------------------------------------------------------------- /doc/_static/PyPLNcluster.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/doc/_static/PyPLNcluster.png -------------------------------------------------------------------------------- /doc/_static/default-pipeline.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/doc/_static/default-pipeline.png -------------------------------------------------------------------------------- /doc/_static/logo_pypln.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/doc/_static/logo_pypln.png -------------------------------------------------------------------------------- /doc/_static/pypln.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/doc/_static/pypln.png -------------------------------------------------------------------------------- /doc/conf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/doc/conf.py -------------------------------------------------------------------------------- /doc/data.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/doc/data.rst -------------------------------------------------------------------------------- /doc/images-source/Pipeline_architecture.graphml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/doc/images-source/Pipeline_architecture.graphml -------------------------------------------------------------------------------- /doc/images-source/PyPLNcluster.graphml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/doc/images-source/PyPLNcluster.graphml -------------------------------------------------------------------------------- /doc/images-source/default-pipeline.dot: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/doc/images-source/default-pipeline.dot -------------------------------------------------------------------------------- /doc/images-source/logo_pypln.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/doc/images-source/logo_pypln.svg -------------------------------------------------------------------------------- /doc/images-source/pypln.graphml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/doc/images-source/pypln.graphml -------------------------------------------------------------------------------- /doc/index.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/doc/index.rst -------------------------------------------------------------------------------- /doc/installation.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/doc/installation.rst -------------------------------------------------------------------------------- /doc/intro.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/doc/intro.rst -------------------------------------------------------------------------------- /doc/logo_pypln.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/doc/logo_pypln.svg -------------------------------------------------------------------------------- /doc/make.bat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/doc/make.bat -------------------------------------------------------------------------------- /doc/parsing.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/doc/parsing.rst -------------------------------------------------------------------------------- /doc/storage.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/doc/storage.rst -------------------------------------------------------------------------------- /doc/text_extraction.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/doc/text_extraction.rst -------------------------------------------------------------------------------- /make-docs.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/make-docs.sh -------------------------------------------------------------------------------- /pypln/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/pypln/__init__.py -------------------------------------------------------------------------------- /pypln/backend/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /pypln/backend/celery_app.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/pypln/backend/celery_app.py -------------------------------------------------------------------------------- /pypln/backend/celery_task.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/pypln/backend/celery_task.py -------------------------------------------------------------------------------- /pypln/backend/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/pypln/backend/config.py -------------------------------------------------------------------------------- /pypln/backend/settings.ini.sample: -------------------------------------------------------------------------------- 1 | [settings] 2 | MONGODB_CONFIG = mongodb://localhost:27017/pypln_dev 3 | -------------------------------------------------------------------------------- /pypln/backend/workers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/pypln/backend/workers/__init__.py -------------------------------------------------------------------------------- /pypln/backend/workers/bigrams.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/pypln/backend/workers/bigrams.py -------------------------------------------------------------------------------- /pypln/backend/workers/elastic_indexer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/pypln/backend/workers/elastic_indexer.py -------------------------------------------------------------------------------- /pypln/backend/workers/extractor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/pypln/backend/workers/extractor.py -------------------------------------------------------------------------------- /pypln/backend/workers/freqdist.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/pypln/backend/workers/freqdist.py -------------------------------------------------------------------------------- /pypln/backend/workers/lemmatizer_pt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/pypln/backend/workers/lemmatizer_pt.py -------------------------------------------------------------------------------- /pypln/backend/workers/palavras_noun_phrase.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/pypln/backend/workers/palavras_noun_phrase.py -------------------------------------------------------------------------------- /pypln/backend/workers/palavras_raw.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/pypln/backend/workers/palavras_raw.py -------------------------------------------------------------------------------- /pypln/backend/workers/palavras_semantic_tagger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/pypln/backend/workers/palavras_semantic_tagger.py -------------------------------------------------------------------------------- /pypln/backend/workers/pos/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/pypln/backend/workers/pos/__init__.py -------------------------------------------------------------------------------- /pypln/backend/workers/pos/en_nltk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/pypln/backend/workers/pos/en_nltk.py -------------------------------------------------------------------------------- /pypln/backend/workers/pos/pt_palavras.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/pypln/backend/workers/pos/pt_palavras.py -------------------------------------------------------------------------------- /pypln/backend/workers/spellchecker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/pypln/backend/workers/spellchecker.py -------------------------------------------------------------------------------- /pypln/backend/workers/statistics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/pypln/backend/workers/statistics.py -------------------------------------------------------------------------------- /pypln/backend/workers/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/pypln/backend/workers/tokenizer.py -------------------------------------------------------------------------------- /pypln/backend/workers/trigrams.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/pypln/backend/workers/trigrams.py -------------------------------------------------------------------------------- /pypln/backend/workers/word_cloud.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/pypln/backend/workers/word_cloud.py -------------------------------------------------------------------------------- /requirements/development.txt: -------------------------------------------------------------------------------- 1 | -r production.txt 2 | 3 | nose 4 | epydoc 5 | sphinx 6 | mock 7 | -------------------------------------------------------------------------------- /requirements/production.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/requirements/production.txt -------------------------------------------------------------------------------- /run_celery.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/run_celery.sh -------------------------------------------------------------------------------- /scripts/add_pipelines.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/scripts/add_pipelines.py -------------------------------------------------------------------------------- /scripts/create_fake_measures.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/scripts/create_fake_measures.py -------------------------------------------------------------------------------- /scripts/mongo2sphinx.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/scripts/mongo2sphinx.py -------------------------------------------------------------------------------- /scripts/sphinx.conf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/scripts/sphinx.conf -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/setup.py -------------------------------------------------------------------------------- /tests/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/data/Mathmodels.rdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/tests/data/Mathmodels.rdf -------------------------------------------------------------------------------- /tests/data/encoding_unknown_to_libmagic.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/tests/data/encoding_unknown_to_libmagic.txt -------------------------------------------------------------------------------- /tests/data/mixed_encoding_not_detected_by_libmagic_or_chardet: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/tests/data/mixed_encoding_not_detected_by_libmagic_or_chardet -------------------------------------------------------------------------------- /tests/data/pypln.conf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/tests/data/pypln.conf -------------------------------------------------------------------------------- /tests/data/random_file: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/tests/data/random_file -------------------------------------------------------------------------------- /tests/data/test.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/tests/data/test.html -------------------------------------------------------------------------------- /tests/data/test.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/tests/data/test.pdf -------------------------------------------------------------------------------- /tests/data/test.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/tests/data/test.txt -------------------------------------------------------------------------------- /tests/data/test_html_entities.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/tests/data/test_html_entities.txt -------------------------------------------------------------------------------- /tests/data/test_iso-8859-1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/tests/data/test_iso-8859-1.txt -------------------------------------------------------------------------------- /tests/test_celery_task.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/tests/test_celery_task.py -------------------------------------------------------------------------------- /tests/test_elastic_indexer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/tests/test_elastic_indexer.py -------------------------------------------------------------------------------- /tests/test_worker_bigrams.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/tests/test_worker_bigrams.py -------------------------------------------------------------------------------- /tests/test_worker_extractor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/tests/test_worker_extractor.py -------------------------------------------------------------------------------- /tests/test_worker_freqdist.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/tests/test_worker_freqdist.py -------------------------------------------------------------------------------- /tests/test_worker_lemmatizer_pt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/tests/test_worker_lemmatizer_pt.py -------------------------------------------------------------------------------- /tests/test_worker_palavras_noun_phrase.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/tests/test_worker_palavras_noun_phrase.py -------------------------------------------------------------------------------- /tests/test_worker_palavras_raw.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/tests/test_worker_palavras_raw.py -------------------------------------------------------------------------------- /tests/test_worker_palavras_semantic_tagger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/tests/test_worker_palavras_semantic_tagger.py -------------------------------------------------------------------------------- /tests/test_worker_pos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/tests/test_worker_pos.py -------------------------------------------------------------------------------- /tests/test_worker_pos_pt_palavras.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/tests/test_worker_pos_pt_palavras.py -------------------------------------------------------------------------------- /tests/test_worker_spellchecker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/tests/test_worker_spellchecker.py -------------------------------------------------------------------------------- /tests/test_worker_statistics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/tests/test_worker_statistics.py -------------------------------------------------------------------------------- /tests/test_worker_tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/tests/test_worker_tokenizer.py -------------------------------------------------------------------------------- /tests/test_worker_trigrams.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/tests/test_worker_trigrams.py -------------------------------------------------------------------------------- /tests/test_worker_wordcloud.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/tests/test_worker_wordcloud.py -------------------------------------------------------------------------------- /tests/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NAMD/pypln.backend/HEAD/tests/utils.py --------------------------------------------------------------------------------