Matt Calder created ARROW-7873:
----------------------------------
Summary: Segfault in pandas version 1.0.1, read_parquet after
creating a clickhouse odbc connection
Key: ARROW-7873
URL: https://issues.apache.org/jira/browse/ARROW-7873
Project: Apache Arrow
Issue Type: Bug
Components: Python
Environment: Ubuntu 18.04
Reporter: Matt Calder
[I posted this issue to the pandas
github|[https://github.com/pandas-dev/pandas/issues/31981]].
We get a segfault when making a call to pd.read_parquet after having made a
connection to clickhouse via odbc. Like so,
{code:python}
import pyodbc
import pandas as pd
con_str = f"Driver=libclickhouseodbc.so;url=http://clickhouse/query;timeout=600"
with pyodbc.connect(con_str, autocommit=True) as con:
pass
df = pd.DataFrame({'A': [1,1,1], 'B': ['a', 'b', 'c']})
df.to_parquet('/tmp/foo.pq')
# This line core dumps:
pd.read_parquet('/tmp/foo.pq')
{code}
This happens with pandas version 1.0.1 but not with pandas 0.25.3. Here's a
stacktrace:
{code:java}
#0 __GI_raise (sig=sig@entry=6) at ../sysdeps/unix/sysv/linux/raise.c:51
#1 0x00007ffff7a24801 in __GI_abort () at abort.c:79
#2 0x00007ffff63c1957 in ?? () from /usr/lib/x86_64-linux-gnu/libstdc++.so.6
#3 0x00007ffff63c7ab6 in ?? () from /usr/lib/x86_64-linux-gnu/libstdc++.so.6
#4 0x00007ffff63c7af1 in std::terminate() () from
/usr/lib/x86_64-linux-gnu/libstdc++.so.6
#5 0x00007ffff63c7d24 in __cxa_throw () from
/usr/lib/x86_64-linux-gnu/libstdc++.so.6
#6 0x00007ffff63c6a52 in __cxa_bad_cast () from
/usr/lib/x86_64-linux-gnu/libstdc++.so.6
#7 0x00007ffff64131ec in std::__cxx11::collate<char> const&
std::use_facet<std::__cxx11::collate<char> >(std::locale const&) () from
/usr/lib/x86_64-linux-gnu/libstdc++.so.6
#8 0x00007fffbe4b8279 in std::__cxx11::basic_string<char,
std::char_traits<char>, std::allocator<char> >
std::__cxx11::regex_traits<char>::transform_primary<char const*>(char const*,
char const*) const () from /usr/local/lib/libparquet.so.100
#9 0x00007fffbe4bd71c in
std::__detail::_BracketMatcher<std::__cxx11::regex_traits<char>, false,
false>::_M_ready() () from /usr/local/lib/libparquet.so.100
#10 0x00007fffbe4bda9e in void
std::__detail::_Compiler<std::__cxx11::regex_traits<char>
>::_M_insert_character_class_matcher<false, false>() () from
/usr/local/lib/libparquet.so.100
#11 0x00007fffbe4c0569 in
std::__detail::_Compiler<std::__cxx11::regex_traits<char> >::_M_atom() () from
/usr/local/lib/libparquet.so.100
#12 0x00007fffbe4c0ad8 in
std::__detail::_Compiler<std::__cxx11::regex_traits<char> >::_M_alternative()
() from /usr/local/lib/libparquet.so.100
#13 0x00007fffbe4c0a43 in
std::__detail::_Compiler<std::__cxx11::regex_traits<char> >::_M_alternative()
() from /usr/local/lib/libparquet.so.100
#14 0x00007fffbe4c0d1c in
std::__detail::_Compiler<std::__cxx11::regex_traits<char> >::_M_disjunction()
() from /usr/local/lib/libparquet.so.100
#15 0x00007fffbe4c1469 in
std::__detail::_Compiler<std::__cxx11::regex_traits<char> >::_Compiler(char
const*, char const*, std::locale const&,
std::regex_constants::syntax_option_type) () from
/usr/local/lib/libparquet.so.100
#16 0x00007fffbe4a93d1 in
parquet::ApplicationVersion::ApplicationVersion(std::__cxx11::basic_string<char,
std::char_traits<char>, std::allocator<char> > const&) () from
/usr/local/lib/libparquet.so.100
#17 0x00007fffbe4c1c03 in
parquet::FileMetaData::FileMetaDataImpl::FileMetaDataImpl(void const*, unsigned
int*, std::shared_ptr<parquet::Decryptor> const&) () from
/usr/local/lib/libparquet.so.100
#18 0x00007fffbe4a9e62 in parquet::FileMetaData::FileMetaData(void const*,
unsigned int*, std::shared_ptr<parquet::Decryptor> const&) () from
/usr/local/lib/libparquet.so.100
#19 0x00007fffbe4a9ec2 in parquet::FileMetaData::Make(void const*, unsigned
int*, std::shared_ptr<parquet::Decryptor> const&) () from
/usr/local/lib/libparquet.so.100
#20 0x00007fffbe48acaf in
parquet::SerializedFile::ParseUnencryptedFileMetadata(std::shared_ptr<arrow::Buffer>
const&, long, long, std::shared_ptr<arrow::Buffer>*, unsigned int*, unsigned
int*) () from /usr/local/lib/libparquet.so.100
#21 0x00007fffbe492d75 in parquet::SerializedFile::ParseMetaData() () from
/usr/local/lib/libparquet.so.100
#22 0x00007fffbe48d8f8 in
parquet::ParquetFileReader::Contents::Open(std::shared_ptr<arrow::io::RandomAccessFile>,
parquet::ReaderProperties const&, std::shared_ptr<parquet::FileMetaData>) ()
from /usr/local/lib/libparquet.so.100
#23 0x00007fffbe48e598 in
parquet::ParquetFileReader::Open(std::shared_ptr<arrow::io::RandomAccessFile>,
parquet::ReaderProperties const&, std::shared_ptr<parquet::FileMetaData>) ()
from /usr/local/lib/libparquet.so.100
#24 0x00007fffbe3a89bd in
parquet::arrow::FileReaderBuilder::Open(std::shared_ptr<arrow::io::RandomAccessFile>,
parquet::ReaderProperties const&, std::shared_ptr<parquet::FileMetaData>) ()
from /usr/local/lib/libparquet.so.100
#25 0x00007fffbe7dc348 in
__pyx_pf_7pyarrow_8_parquet_13ParquetReader_2open(__pyx_obj_7pyarrow_8_parquet_ParquetReader*,
_object*, int, _object*, __pyx_obj_7pyarrow_8_parquet_FileMetaData*, int) ()
from
/usr/local/lib/python3.6/dist-packages/pyarrow-0.15.1.dev539+g8cf0c8e0a-py3.6-linux-x86_64.egg/pyarrow/_parquet.cpython-36m-x86_64-linux-gnu.so
#26 0x00007fffbe7dcbc9 in
__pyx_pw_7pyarrow_8_parquet_13ParquetReader_3open(_object*, _object*, _object*)
() from
/usr/local/lib/python3.6/dist-packages/pyarrow-0.15.1.dev539+g8cf0c8e0a-py3.6-linux-x86_64.egg/pyarrow/_parquet.cpython-36m-x86_64-linux-gnu.so
#27 0x000000000050ac25 in _PyCFunction_FastCallDict (kwargs=<optimized out>,
nargs=<optimized out>, args=<optimized out>, func_obj=<built-in method open of
pyarrow._parquet.ParquetReader object at remote 0x7fffbfc6b938>) at
../Objects/methodobject.c:231
#28 _PyCFunction_FastCallKeywords (kwnames=<optimized out>, nargs=<optimized
out>, stack=<optimized out>, func=<optimized out>) at
../Objects/methodobject.c:294
#29 call_function.lto_priv () at ../Python/ceval.c:4851
#30 0x000000000050d390 in _PyEval_EvalFrameDefault () at ../Python/ceval.c:3351
#31 0x0000000000508245 in PyEval_EvalFrameEx (throwflag=0, f=
Frame 0x142a818, for file
/usr/local/lib/python3.6/dist-packages/pyarrow-0.15.1.dev539+g8cf0c8e0a-py3.6-linux-x86_64.egg/pyarrow/parquet.py,
line 137, in __init__
(self=<ParquetFile(reader=<pyarrow._parquet.ParquetReader at remote
0x7fffbfc6b938>) at remote 0x7fffc4b68cc0>, source='/tmp/foo.pq',
metadata=None, common_metadata=None, read_dictionary=None, memory_map=False,
buffer_size=0)) at ../Python/ceval.c:754
#32 _PyEval_EvalCodeWithName.lto_priv.1836 () at ../Python/ceval.c:4166
#33 0x0000000000509642 in _PyFunction_FastCallDict () at ../Python/ceval.c:5075
#34 0x0000000000595311 in _PyObject_FastCallDict (kwargs={'metadata': None,
'memory_map': False, 'read_dictionary': None, 'common_metadata': None,
'buffer_size': 0}, nargs=2, args=0x7fffffffc430, func=<function at remote
0x7fffbfc5e378>)
at ../Objects/abstract.c:2310
#35 _PyObject_Call_Prepend (kwargs={'metadata': None, 'memory_map': False,
'read_dictionary': None, 'common_metadata': None, 'buffer_size': 0},
args=<optimized out>, obj=<optimized out>, func=<function at remote
0x7fffbfc5e378>) at ../Objects/abstract.c:2373
#36 method_call.lto_priv () at ../Objects/classobject.c:314
#37 0x000000000054a6ff in PyObject_Call (kwargs={'metadata': None,
'memory_map': False, 'read_dictionary': None, 'common_metadata': None,
'buffer_size': 0}, args=('/tmp/foo.pq',), func=<method at remote
0x7ffff7f67fc8>) at ../Objects/abstract.c:2261
#38 slot_tp_init () at ../Objects/typeobject.c:6420
#39 0x0000000000551b81 in type_call.lto_priv () at ../Objects/typeobject.c:915
---Type <return> to continue, or q <return> to quit---
{code}
--
This message was sent by Atlassian Jira
(v8.3.4#803005)