[
https://issues.apache.org/jira/browse/ARROW-586?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Adam Szałucha updated ARROW-586:
--------------------------------
Description:
When I try to read parquet file saved by Apache Spark I get the following error
---------------------------------------------------------------------------
ArrowException Traceback (most recent call last)
<ipython-input-14-6dfa089b9299> in <module>()
----> 1 table = pq.read_multiple_files(files2)
/Users/adremja/miniconda3/lib/python3.6/site-packages/pyarrow/parquet.py in
read_multiple_files(paths, columns, filesystem, nthreads, metadata, schema)
141
142 if metadata is None and schema is None:
--> 143 schema = open_file(paths[0]).schema
144 elif schema is None:
145 schema = metadata.schema
/Users/adremja/miniconda3/lib/python3.6/site-packages/pyarrow/parquet.py in
open_file(path, meta)
132 if filesystem is None:
133 def open_file(path, meta=None):
--> 134 return ParquetFile(path, metadata=meta)
135 else:
136 def open_file(path, meta=None):
/Users/adremja/miniconda3/lib/python3.6/site-packages/pyarrow/parquet.py in
__init__(self, source, metadata)
36 def __init__(self, source, metadata=None):
37 self.reader = ParquetReader()
---> 38 self.reader.open(source, metadata=metadata)
39
40 @property
/Users/adremja/miniconda3/lib/python3.6/site-packages/pyarrow/_parquet.pyx in
pyarrow._parquet.ParquetReader.open
(/Users/travis/miniconda3/conda-bld/recipe_1485750760150/work/arrow-7ac320bde52ae47007dadac7398e22a203c6a48d/python/build/temp.macosx-10.9-x86_64-3.6/_parquet.cxx:7144)()
/Users/adremja/miniconda3/lib/python3.6/site-packages/pyarrow/io.pyx in
pyarrow.io.get_reader
(/Users/travis/miniconda3/conda-bld/recipe_1485750760150/work/arrow-7ac320bde52ae47007dadac7398e22a203c6a48d/python/build/temp.macosx-10.9-x86_64-3.6/io.cxx:9489)()
/Users/adremja/miniconda3/lib/python3.6/site-packages/pyarrow/io.pyx in
pyarrow.io.MemoryMappedFile.__cinit__
(/Users/travis/miniconda3/conda-bld/recipe_1485750760150/work/arrow-7ac320bde52ae47007dadac7398e22a203c6a48d/python/build/temp.macosx-10.9-x86_64-3.6/io.cxx:7732)()
/Users/adremja/miniconda3/lib/python3.6/site-packages/pyarrow/error.pyx in
pyarrow.error.check_status
(/Users/travis/miniconda3/conda-bld/recipe_1485750760150/work/arrow-7ac320bde52ae47007dadac7398e22a203c6a48d/python/build/temp.macosx-10.9-x86_64-3.6/error.cxx:1197)()
ArrowException: IOError: Failed to open file:
part-00000-2066b71b-c55f-411a-a682-4cc94ddb6d16.snappy.parquet
was:
When I try to read parquet file I get the following error
---------------------------------------------------------------------------
ArrowException Traceback (most recent call last)
<ipython-input-14-6dfa089b9299> in <module>()
----> 1 table = pq.read_multiple_files(files2)
/Users/adremja/miniconda3/lib/python3.6/site-packages/pyarrow/parquet.py in
read_multiple_files(paths, columns, filesystem, nthreads, metadata, schema)
141
142 if metadata is None and schema is None:
--> 143 schema = open_file(paths[0]).schema
144 elif schema is None:
145 schema = metadata.schema
/Users/adremja/miniconda3/lib/python3.6/site-packages/pyarrow/parquet.py in
open_file(path, meta)
132 if filesystem is None:
133 def open_file(path, meta=None):
--> 134 return ParquetFile(path, metadata=meta)
135 else:
136 def open_file(path, meta=None):
/Users/adremja/miniconda3/lib/python3.6/site-packages/pyarrow/parquet.py in
__init__(self, source, metadata)
36 def __init__(self, source, metadata=None):
37 self.reader = ParquetReader()
---> 38 self.reader.open(source, metadata=metadata)
39
40 @property
/Users/adremja/miniconda3/lib/python3.6/site-packages/pyarrow/_parquet.pyx in
pyarrow._parquet.ParquetReader.open
(/Users/travis/miniconda3/conda-bld/recipe_1485750760150/work/arrow-7ac320bde52ae47007dadac7398e22a203c6a48d/python/build/temp.macosx-10.9-x86_64-3.6/_parquet.cxx:7144)()
/Users/adremja/miniconda3/lib/python3.6/site-packages/pyarrow/io.pyx in
pyarrow.io.get_reader
(/Users/travis/miniconda3/conda-bld/recipe_1485750760150/work/arrow-7ac320bde52ae47007dadac7398e22a203c6a48d/python/build/temp.macosx-10.9-x86_64-3.6/io.cxx:9489)()
/Users/adremja/miniconda3/lib/python3.6/site-packages/pyarrow/io.pyx in
pyarrow.io.MemoryMappedFile.__cinit__
(/Users/travis/miniconda3/conda-bld/recipe_1485750760150/work/arrow-7ac320bde52ae47007dadac7398e22a203c6a48d/python/build/temp.macosx-10.9-x86_64-3.6/io.cxx:7732)()
/Users/adremja/miniconda3/lib/python3.6/site-packages/pyarrow/error.pyx in
pyarrow.error.check_status
(/Users/travis/miniconda3/conda-bld/recipe_1485750760150/work/arrow-7ac320bde52ae47007dadac7398e22a203c6a48d/python/build/temp.macosx-10.9-x86_64-3.6/error.cxx:1197)()
ArrowException: IOError: Failed to open file:
part-00000-2066b71b-c55f-411a-a682-4cc94ddb6d16.snappy.parquet
> Problem with reading parquet files saved by Apache Spark
> --------------------------------------------------------
>
> Key: ARROW-586
> URL: https://issues.apache.org/jira/browse/ARROW-586
> Project: Apache Arrow
> Issue Type: Bug
> Components: Python
> Affects Versions: 0.1.0
> Reporter: Adam Szałucha
>
> When I try to read parquet file saved by Apache Spark I get the following
> error
> ---------------------------------------------------------------------------
> ArrowException Traceback (most recent call last)
> <ipython-input-14-6dfa089b9299> in <module>()
> ----> 1 table = pq.read_multiple_files(files2)
> /Users/adremja/miniconda3/lib/python3.6/site-packages/pyarrow/parquet.py in
> read_multiple_files(paths, columns, filesystem, nthreads, metadata, schema)
> 141
> 142 if metadata is None and schema is None:
> --> 143 schema = open_file(paths[0]).schema
> 144 elif schema is None:
> 145 schema = metadata.schema
> /Users/adremja/miniconda3/lib/python3.6/site-packages/pyarrow/parquet.py in
> open_file(path, meta)
> 132 if filesystem is None:
> 133 def open_file(path, meta=None):
> --> 134 return ParquetFile(path, metadata=meta)
> 135 else:
> 136 def open_file(path, meta=None):
> /Users/adremja/miniconda3/lib/python3.6/site-packages/pyarrow/parquet.py in
> __init__(self, source, metadata)
> 36 def __init__(self, source, metadata=None):
> 37 self.reader = ParquetReader()
> ---> 38 self.reader.open(source, metadata=metadata)
> 39
> 40 @property
> /Users/adremja/miniconda3/lib/python3.6/site-packages/pyarrow/_parquet.pyx in
> pyarrow._parquet.ParquetReader.open
> (/Users/travis/miniconda3/conda-bld/recipe_1485750760150/work/arrow-7ac320bde52ae47007dadac7398e22a203c6a48d/python/build/temp.macosx-10.9-x86_64-3.6/_parquet.cxx:7144)()
> /Users/adremja/miniconda3/lib/python3.6/site-packages/pyarrow/io.pyx in
> pyarrow.io.get_reader
> (/Users/travis/miniconda3/conda-bld/recipe_1485750760150/work/arrow-7ac320bde52ae47007dadac7398e22a203c6a48d/python/build/temp.macosx-10.9-x86_64-3.6/io.cxx:9489)()
> /Users/adremja/miniconda3/lib/python3.6/site-packages/pyarrow/io.pyx in
> pyarrow.io.MemoryMappedFile.__cinit__
> (/Users/travis/miniconda3/conda-bld/recipe_1485750760150/work/arrow-7ac320bde52ae47007dadac7398e22a203c6a48d/python/build/temp.macosx-10.9-x86_64-3.6/io.cxx:7732)()
> /Users/adremja/miniconda3/lib/python3.6/site-packages/pyarrow/error.pyx in
> pyarrow.error.check_status
> (/Users/travis/miniconda3/conda-bld/recipe_1485750760150/work/arrow-7ac320bde52ae47007dadac7398e22a203c6a48d/python/build/temp.macosx-10.9-x86_64-3.6/error.cxx:1197)()
> ArrowException: IOError: Failed to open file:
> part-00000-2066b71b-c55f-411a-a682-4cc94ddb6d16.snappy.parquet
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
