This is one of the test pipelines included in Pimlico's repository. See test-pipelines
for more details.
The complete config file for this test pipeline:
[pipeline]
name=concat
release=latest
# Take input from some prepared Pimlico datasets
[europarl1]
type=pimlico.datatypes.corpora.GroupedCorpus
data_point_type=RawTextDocumentType
dir=%(test_data_dir)s/datasets/text_corpora/europarl
[europarl2]
type=pimlico.datatypes.corpora.GroupedCorpus
data_point_type=RawTextDocumentType
dir=%(test_data_dir)s/datasets/text_corpora/europarl2
[concat]
type=pimlico.modules.corpora.concat
input_corpora=europarl1,europarl2
[output]
type=pimlico.modules.corpora.format
The following Pimlico module types are used in this pipeline:
pimlico.modules.corpora.concat
pimlico.modules.corpora.format