├── .gitignore ├── LICENSE.md ├── README.md ├── de1 ├── __init__.py ├── airtable │ ├── __init__.py │ └── airtable_data_set.py ├── empty │ ├── __init__.py │ └── empty_partitioned_data_set.py ├── lazy │ ├── __init__.py │ └── lazy_partitioned_data_set.py ├── pdf │ ├── __init__.py │ ├── pdf_data_set.py │ └── pdf_page.py ├── tests │ ├── __init__.py │ ├── test_empty │ │ ├── __init__.py │ │ └── test_empty_partitioned_data_set.py │ ├── test_lazy │ │ ├── __init__.py │ │ └── test_lazy_partitioned_data_set.py │ ├── test_pdf │ │ ├── __init__.py │ │ ├── data │ │ │ ├── simple.pdf │ │ │ └── table.pdf │ │ └── test_pdf_data_set.py │ └── test_zip │ │ ├── __init__.py │ │ ├── data │ │ ├── csv.zip │ │ ├── dir.zip │ │ ├── ignored_file.zip │ │ ├── simple_pdf.zip │ │ └── two_pdfs.zip │ │ └── test_zip_file_data_set.py └── zip │ ├── __init__.py │ └── zip_file_data_set.py ├── images └── logo.png ├── publish.sh └── setup.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dataengineerone/de1-python/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dataengineerone/de1-python/HEAD/LICENSE.md -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dataengineerone/de1-python/HEAD/README.md -------------------------------------------------------------------------------- /de1/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dataengineerone/de1-python/HEAD/de1/__init__.py -------------------------------------------------------------------------------- /de1/airtable/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /de1/airtable/airtable_data_set.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dataengineerone/de1-python/HEAD/de1/airtable/airtable_data_set.py -------------------------------------------------------------------------------- /de1/empty/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dataengineerone/de1-python/HEAD/de1/empty/__init__.py -------------------------------------------------------------------------------- /de1/empty/empty_partitioned_data_set.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dataengineerone/de1-python/HEAD/de1/empty/empty_partitioned_data_set.py -------------------------------------------------------------------------------- /de1/lazy/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dataengineerone/de1-python/HEAD/de1/lazy/__init__.py -------------------------------------------------------------------------------- /de1/lazy/lazy_partitioned_data_set.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dataengineerone/de1-python/HEAD/de1/lazy/lazy_partitioned_data_set.py -------------------------------------------------------------------------------- /de1/pdf/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dataengineerone/de1-python/HEAD/de1/pdf/__init__.py -------------------------------------------------------------------------------- /de1/pdf/pdf_data_set.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dataengineerone/de1-python/HEAD/de1/pdf/pdf_data_set.py -------------------------------------------------------------------------------- /de1/pdf/pdf_page.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dataengineerone/de1-python/HEAD/de1/pdf/pdf_page.py -------------------------------------------------------------------------------- /de1/tests/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /de1/tests/test_empty/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /de1/tests/test_empty/test_empty_partitioned_data_set.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dataengineerone/de1-python/HEAD/de1/tests/test_empty/test_empty_partitioned_data_set.py -------------------------------------------------------------------------------- /de1/tests/test_lazy/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /de1/tests/test_lazy/test_lazy_partitioned_data_set.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dataengineerone/de1-python/HEAD/de1/tests/test_lazy/test_lazy_partitioned_data_set.py -------------------------------------------------------------------------------- /de1/tests/test_pdf/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /de1/tests/test_pdf/data/simple.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dataengineerone/de1-python/HEAD/de1/tests/test_pdf/data/simple.pdf -------------------------------------------------------------------------------- /de1/tests/test_pdf/data/table.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dataengineerone/de1-python/HEAD/de1/tests/test_pdf/data/table.pdf -------------------------------------------------------------------------------- /de1/tests/test_pdf/test_pdf_data_set.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dataengineerone/de1-python/HEAD/de1/tests/test_pdf/test_pdf_data_set.py -------------------------------------------------------------------------------- /de1/tests/test_zip/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /de1/tests/test_zip/data/csv.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dataengineerone/de1-python/HEAD/de1/tests/test_zip/data/csv.zip -------------------------------------------------------------------------------- /de1/tests/test_zip/data/dir.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dataengineerone/de1-python/HEAD/de1/tests/test_zip/data/dir.zip -------------------------------------------------------------------------------- /de1/tests/test_zip/data/ignored_file.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dataengineerone/de1-python/HEAD/de1/tests/test_zip/data/ignored_file.zip -------------------------------------------------------------------------------- /de1/tests/test_zip/data/simple_pdf.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dataengineerone/de1-python/HEAD/de1/tests/test_zip/data/simple_pdf.zip -------------------------------------------------------------------------------- /de1/tests/test_zip/data/two_pdfs.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dataengineerone/de1-python/HEAD/de1/tests/test_zip/data/two_pdfs.zip -------------------------------------------------------------------------------- /de1/tests/test_zip/test_zip_file_data_set.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dataengineerone/de1-python/HEAD/de1/tests/test_zip/test_zip_file_data_set.py -------------------------------------------------------------------------------- /de1/zip/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dataengineerone/de1-python/HEAD/de1/zip/__init__.py -------------------------------------------------------------------------------- /de1/zip/zip_file_data_set.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dataengineerone/de1-python/HEAD/de1/zip/zip_file_data_set.py -------------------------------------------------------------------------------- /images/logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dataengineerone/de1-python/HEAD/images/logo.png -------------------------------------------------------------------------------- /publish.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dataengineerone/de1-python/HEAD/publish.sh -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/dataengineerone/de1-python/HEAD/setup.py --------------------------------------------------------------------------------