Python Pipeline.add_store Examples

Example #1

File: basic_pipeline_tests.py Project: kodexa-ai/kodexa

def test_table_stores_with_extractor():
    document_store = LocalDocumentStore()
    document_store.put("test.doc", create_document())
    pipeline = Pipeline(document_store, stop_on_exception=False)
    pipeline.add_store('output', TableDataStore(columns=['cheese']))

    def extractor(document, context):
        # An example of how we might
        # extract into a dict
        #
        context.get_store('output').add(['test'])

        return document

    pipeline.add_step(extractor)

    context = pipeline.run()

    assert context.get_store('output').count() == 1

Example #2

File: basic_pipeline_tests.py Project: fossabot/kodexa

def test_table_stores_with_extractor():
    document_store = JsonDocumentStore("/tmp/test-json-store",
                                       force_initialize=True)
    document_store.add(create_document())
    pipeline = Pipeline(document_store, stop_on_exception=False)
    pipeline.add_store('output', TableDataStore(columns=['cheese']))

    def extractor(document, context):
        # An example of how we might
        # extract into a dict
        #
        context.get_store('output').add(['test'])

        return document

    pipeline.add_step(extractor)

    context = pipeline.run()

    assert pipeline.context.get_store('output').count() == 1

Example #3

File: basic_pipeline_tests.py Project: fossabot/kodexa

def test_dict_stores_with_extractor():
    document_store = JsonDocumentStore("/tmp/test-json-store",
                                       force_initialize=True)
    document_store.add(create_document())
    pipeline = Pipeline(document_store, stop_on_exception=False)
    pipeline.add_store('output', DictDataStore())

    def extractor(document, context):
        # An example of how we might
        # extract into a dict
        #
        context.get_store('output').add({'cheese': 'test'})

        return document

    pipeline.add_step(extractor)

    stats = pipeline.run().statistics

    assert pipeline.context.get_store('output').count() == 1