Processing batch 1/4 [{'luxwort': [1906, 1920]}]
Processing year 1906
Retrieving issues...
/scratch/matteo/impresso/solr-rebuilt/luxwort-1906
Fleshing out articles by issue...
Number of partitions: 108
Traceback (most recent call last):
File "impresso_commons/text/rebuilder.py", line 623, in <module>
main()
File "impresso_commons/text/rebuilder.py", line 607, in main
format=output_format
File "impresso_commons/text/rebuilder.py", line 501, in rebuild_issues
.to_textfiles('{}/*.json'.format(issue_dir))
File "/home/romanell/.local/share/virtualenvs/impresso-pycommons-r-mvz05T/lib/python3.6/site-packages/dask/bag/core.py", line 720, in to_textfiles
last_endline=last_endline, **kwargs)
File "/home/romanell/.local/share/virtualenvs/impresso-pycommons-r-mvz05T/lib/python3.6/site-packages/dask/bag/core.py", line 213, in to_textfiles
out.compute(**kwargs)
File "/home/romanell/.local/share/virtualenvs/impresso-pycommons-r-mvz05T/lib/python3.6/site-packages/dask/base.py", line 156, in compute
(result,) = compute(self, traverse=False, **kwargs)
File "/home/romanell/.local/share/virtualenvs/impresso-pycommons-r-mvz05T/lib/python3.6/site-packages/dask/base.py", line 398, in compute
results = schedule(dsk, keys, **kwargs)
File "/home/romanell/.local/share/virtualenvs/impresso-pycommons-r-mvz05T/lib/python3.6/site-packages/distributed/client.py", line 2545, in get
results = self.gather(packed, asynchronous=asynchronous, direct=direct)
File "/home/romanell/.local/share/virtualenvs/impresso-pycommons-r-mvz05T/lib/python3.6/site-packages/distributed/client.py", line 1800, in gather
asynchronous=asynchronous,
File "/home/romanell/.local/share/virtualenvs/impresso-pycommons-r-mvz05T/lib/python3.6/site-packages/distributed/client.py", line 739, in sync
return sync(self.loop, func, *args, **kwargs)
File "/home/romanell/.local/share/virtualenvs/impresso-pycommons-r-mvz05T/lib/python3.6/site-packages/distributed/utils.py", line 331, in sync
six.reraise(*error[0])
File "/home/romanell/.local/share/virtualenvs/impresso-pycommons-r-mvz05T/lib/python3.6/site-packages/six.py", line 693, in reraise
raise value
File "/home/romanell/.local/share/virtualenvs/impresso-pycommons-r-mvz05T/lib/python3.6/site-packages/distributed/utils.py", line 316, in f
result[0] = yield future
File "/home/romanell/.local/share/virtualenvs/impresso-pycommons-r-mvz05T/lib/python3.6/site-packages/tornado/gen.py", line 729, in run
value = future.result()
File "/home/romanell/.local/share/virtualenvs/impresso-pycommons-r-mvz05T/lib/python3.6/site-packages/tornado/gen.py", line 736, in run
yielded = self.gen.throw(*exc_info) # type: ignore
File "/home/romanell/.local/share/virtualenvs/impresso-pycommons-r-mvz05T/lib/python3.6/site-packages/distributed/client.py", line 1631, in _gather
six.reraise(type(exception), exception, traceback)
File "/home/romanell/.local/share/virtualenvs/impresso-pycommons-r-mvz05T/lib/python3.6/site-packages/six.py", line 692, in reraise
raise value.with_traceback(tb)
File "/home/romanell/.local/share/virtualenvs/impresso-pycommons-r-mvz05T/lib/python3.6/site-packages/dask/bag/core.py", line 132, in _to_textfiles_chunk
for d in data:
File "/home/romanell/.local/share/virtualenvs/impresso-pycommons-r-mvz05T/lib/python3.6/site-packages/dask/bag/core.py", line 1750, in map_chunk
for a in zip(*args):
File "/home/romanell/.local/share/virtualenvs/impresso-pycommons-r-mvz05T/lib/python3.6/site-packages/dask/bag/core.py", line 1750, in map_chunk
for a in zip(*args):
File "/home/romanell/impresso_code/impresso-pycommons/impresso_commons/text/helpers.py", line 91, in rejoin_articles
][0]
IndexError: list index out of range
stacktrace: